oxi-ai 0.16.0

//! Comprehensive model database for oxi-ai
//!
//! Contains 544 models across 28 providers.
//!
//! # Usage
//!
//! ```ignore
//! use oxi_ai::model_db::{get_model_entry, get_provider_models, get_all_models};
//!
//! // Look up a specific model
//! let entry = get_model_entry("anthropic", "claude-sonnet-4-20250514");
//! assert!(entry.is_some());
//!
//! // Get all models for a provider
//! let anthropic_models = get_provider_models("anthropic");
//! assert!(!anthropic_models.is_empty());
//!
//! // Iterate all models
//! let all = get_all_models();
//! assert!(all.len() > 534);
//! ```

use crate::{Api, InputModality};

/// A static model entry in the database.
///
/// Uses `&'static str` references for zero-allocation lookups.
#[derive(Debug, Clone, Copy, PartialEq)]
pub struct ModelEntry {
    /// Model identifier (e.g., "claude-sonnet-4-20250514")
    pub id: &'static str,
    /// Human-readable model name (e.g., "Claude Sonnet 4")
    pub name: &'static str,
    /// API protocol to use
    pub api: Api,
    /// Provider name (e.g., "anthropic", "openai")
    pub provider: &'static str,
    /// Whether this model supports reasoning/thinking
    pub reasoning: bool,
    /// Supported input modalities
    pub input: &'static [InputModality],
    /// Cost per million input tokens (USD)
    pub cost_input: f64,
    /// Cost per million output tokens (USD)
    pub cost_output: f64,
    /// Cost per million cached read tokens (USD)
    pub cost_cache_read: f64,
    /// Cost per million cached write tokens (USD)
    pub cost_cache_write: f64,
    /// Maximum context window in tokens
    pub context_window: u32,
    /// Maximum output tokens
    pub max_tokens: u32,
}

impl ModelEntry {
    /// Check if this model supports image/vision input
    pub fn supports_vision(&self) -> bool {
        self.input.contains(&InputModality::Image)
    }

    /// Check if this model supports reasoning/thinking
    pub fn supports_reasoning(&self) -> bool {
        self.reasoning
    }

    /// Calculate the cost for a given token usage
    pub fn calculate_cost(
        &self,
        input_tokens: u64,
        output_tokens: u64,
        cache_read: u64,
        cache_write: u64,
    ) -> f64 {
        let in_cost = (input_tokens as f64 / 1_000_000.0) * self.cost_input;
        let out_cost = (output_tokens as f64 / 1_000_000.0) * self.cost_output;
        let cr_cost = (cache_read as f64 / 1_000_000.0) * self.cost_cache_read;
        let cw_cost = (cache_write as f64 / 1_000_000.0) * self.cost_cache_write;
        in_cost + out_cost + cr_cost + cw_cost
    }
}

/// amazon-bedrock models (50 entries)
static AMAZON_BEDROCK_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "amazon.nova-2-lite-v1:0",
        name: "Nova 2 Lite",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "amazon.nova-lite-v1:0",
        name: "Nova Lite",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.015,
        cost_cache_write: 0.0,
        context_window: 300000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "amazon.nova-premier-v1:0",
        name: "Nova Premier",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "anthropic.claude-3-5-haiku-20241022-v1:0",
        name: "Claude Haiku 3.5",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 1.0,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "anthropic.claude-3-5-sonnet-20241022-v2:0",
        name: "Claude Sonnet 3.5 v2",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "anthropic.claude-3-haiku-20240307-v1:0",
        name: "Claude Haiku 3",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "anthropic.claude-opus-4-1-20250805-v1:0",
        name: "Claude Opus 4.1",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "anthropic.claude-opus-4-5-20251101-v1:0",
        name: "Claude Opus 4.5",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "anthropic.claude-opus-4-6-v1",
        name: "Claude Opus 4.6",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "anthropic.claude-sonnet-4-20250514-v1:0",
        name: "Claude Sonnet 4",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "anthropic.claude-sonnet-4-6",
        name: "Claude Sonnet 4.6",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "au.anthropic.claude-sonnet-4-6",
        name: "AU Anthropic Claude Sonnet 4.6",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.33,
        cost_cache_write: 4.125,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "deepseek.v3-v1:0",
        name: "DeepSeek-V3.1",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 163840,
        max_tokens: 81920,
    },
    ModelEntry {
        id: "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
        name: "Claude Haiku 4.5 (EU)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "eu.anthropic.claude-opus-4-6-v1",
        name: "Claude Opus 4.6 (EU)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "eu.anthropic.claude-opus-4-7",
        name: "Claude Opus 4.7 (EU)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
        name: "Claude Sonnet 4.5 (EU)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
        name: "Claude Haiku 4.5 (Global)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "global.anthropic.claude-opus-4-6-v1",
        name: "Claude Opus 4.6 (Global)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
        name: "Claude Sonnet 4 (Global)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "global.anthropic.claude-sonnet-4-6",
        name: "Claude Sonnet 4.6 (Global)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "google.gemma-3-4b-it",
        name: "Gemma 3 4B IT",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "meta.llama3-1-405b-instruct-v1:0",
        name: "Llama 3.1 405B Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "meta.llama3-1-8b-instruct-v1:0",
        name: "Llama 3.1 8B Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "meta.llama3-2-1b-instruct-v1:0",
        name: "Llama 3.2 1B Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "meta.llama3-2-90b-instruct-v1:0",
        name: "Llama 3.2 90B Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "meta.llama4-maverick-17b-instruct-v1:0",
        name: "Llama 4 Maverick 17B Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "minimax.minimax-m2",
        name: "MiniMax M2",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 204608,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "minimax.minimax-m2.5",
        name: "MiniMax M2.5",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 196608,
        max_tokens: 98304,
    },
    ModelEntry {
        id: "mistral.devstral-2-123b",
        name: "Devstral 2 123B",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "mistral.ministral-3-14b-instruct",
        name: "Ministral 14B 3.0",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "mistral.ministral-3-8b-instruct",
        name: "Ministral 3 8B",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "mistral.pixtral-large-2502-v1:0",
        name: "Pixtral Large (25.02)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "mistral.voxtral-small-24b-2507",
        name: "Voxtral Small 24B 2507",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 32000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "moonshotai.kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "nvidia.nemotron-nano-3-30b",
        name: "NVIDIA Nemotron Nano 3 30B",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "nvidia.nemotron-nano-9b-v2",
        name: "NVIDIA Nemotron Nano 9B v2",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "openai.gpt-oss-120b-1:0",
        name: "gpt-oss-120b",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "openai.gpt-oss-safeguard-120b",
        name: "GPT OSS Safeguard 120B",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "qwen.qwen3-235b-a22b-2507-v1:0",
        name: "Qwen3 235B A22B 2507",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "qwen.qwen3-coder-30b-a3b-v1:0",
        name: "Qwen3 Coder 30B A3B Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "qwen.qwen3-coder-next",
        name: "Qwen3 Coder Next",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "qwen.qwen3-vl-235b-a22b",
        name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262000,
        max_tokens: 262000,
    },
    ModelEntry {
        id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
        name: "Claude Haiku 4.5 (US)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "us.anthropic.claude-opus-4-20250514-v1:0",
        name: "Claude Opus 4 (US)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "us.anthropic.claude-opus-4-6-v1",
        name: "Claude Opus 4.6 (US)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
        name: "Claude Sonnet 4 (US)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "us.anthropic.claude-sonnet-4-6",
        name: "Claude Sonnet 4.6 (US)",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "writer.palmyra-x5-v1:0",
        name: "Palmyra X5",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1040000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "zai.glm-4.7-flash",
        name: "GLM-4.7-Flash",
        api: Api::BedrockConverseStream,
        provider: "amazon-bedrock",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 131072,
    },
];

/// anthropic models (23 entries)
static ANTHROPIC_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "claude-3-5-haiku-20241022",
        name: "Claude Haiku 3.5",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 1.0,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "claude-3-5-haiku-latest",
        name: "Claude Haiku 3.5 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 1.0,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "claude-3-5-sonnet-20240620",
        name: "Claude Sonnet 3.5",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "claude-3-5-sonnet-20241022",
        name: "Claude Sonnet 3.5 v2",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "claude-3-7-sonnet-20250219",
        name: "Claude Sonnet 3.7",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-3-haiku-20240307",
        name: "Claude Haiku 3",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.3,
        context_window: 200000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "claude-3-opus-20240229",
        name: "Claude Opus 3",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "claude-3-sonnet-20240229",
        name: "Claude Sonnet 3",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 0.3,
        context_window: 200000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "claude-haiku-4-5",
        name: "Claude Haiku 4.5 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-haiku-4-5-20251001",
        name: "Claude Haiku 4.5",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-opus-4-0",
        name: "Claude Opus 4 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-1",
        name: "Claude Opus 4.1 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-1-20250805",
        name: "Claude Opus 4.1",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-20250514",
        name: "Claude Opus 4",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-5",
        name: "Claude Opus 4.5 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-opus-4-5-20251101",
        name: "Claude Opus 4.5",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-opus-4-6",
        name: "Claude Opus 4.6",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "claude-opus-4-7",
        name: "Claude Opus 4.7",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "claude-sonnet-4-0",
        name: "Claude Sonnet 4 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-20250514",
        name: "Claude Sonnet 4",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-5",
        name: "Claude Sonnet 4.5 (latest)",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-5-20250929",
        name: "Claude Sonnet 4.5",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-6",
        name: "Claude Sonnet 4.6",
        api: Api::AnthropicMessages,
        provider: "anthropic",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
];

/// azure-openai-responses models (42 entries)
static AZURE_OPENAI_RESPONSES_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "gpt-4",
        name: "GPT-4",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gpt-4-turbo",
        name: "GPT-4 Turbo",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "gpt-4.1",
        name: "GPT-4.1",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "gpt-4.1-mini",
        name: "GPT-4.1 mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "gpt-4.1-nano",
        name: "GPT-4.1 nano",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "gpt-4o",
        name: "GPT-4o",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o-2024-05-13",
        name: "GPT-4o (2024-05-13)",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "gpt-4o-2024-08-06",
        name: "GPT-4o (2024-08-06)",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o-2024-11-20",
        name: "GPT-4o (2024-11-20)",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o-mini",
        name: "GPT-4o mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5",
        name: "GPT-5",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-chat-latest",
        name: "GPT-5 Chat Latest",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5-codex",
        name: "GPT-5-Codex",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-mini",
        name: "GPT-5 Mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-nano",
        name: "GPT-5 Nano",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.005,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-pro",
        name: "GPT-5 Pro",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 272000,
    },
    ModelEntry {
        id: "gpt-5.1",
        name: "GPT-5.1",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.13,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-chat-latest",
        name: "GPT-5.1 Chat",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.1-codex",
        name: "GPT-5.1 Codex",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-max",
        name: "GPT-5.1 Codex Max",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-mini",
        name: "GPT-5.1 Codex mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2",
        name: "GPT-5.2",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-chat-latest",
        name: "GPT-5.2 Chat",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.2-codex",
        name: "GPT-5.2 Codex",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-pro",
        name: "GPT-5.2 Pro",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-chat-latest",
        name: "GPT-5.3 Chat (latest)",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.3-codex",
        name: "GPT-5.3 Codex",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-codex-spark",
        name: "GPT-5.3 Codex Spark",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "gpt-5.4",
        name: "GPT-5.4",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.25,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-mini",
        name: "GPT-5.4 mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-nano",
        name: "GPT-5.4 nano",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-pro",
        name: "GPT-5.4 Pro",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5",
        name: "GPT-5.5",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5-pro",
        name: "GPT-5.5 Pro",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "o1",
        name: "o1",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 7.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o1-pro",
        name: "o1-pro",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3",
        name: "o3",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-deep-research",
        name: "o3-deep-research",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-mini",
        name: "o3-mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.55,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-pro",
        name: "o3-pro",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o4-mini",
        name: "o4-mini",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.28,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o4-mini-deep-research",
        name: "o4-mini-deep-research",
        api: Api::AzureOpenAiResponses,
        provider: "azure-openai-responses",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
];

/// cerebras models (4 entries)
static CEREBRAS_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "gpt-oss-120b",
        name: "GPT OSS 120B",
        api: Api::OpenAiCompletions,
        provider: "cerebras",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "llama3.1-8b",
        name: "Llama 3.1 8B",
        api: Api::OpenAiCompletions,
        provider: "cerebras",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 32000,
        max_tokens: 8000,
    },
    ModelEntry {
        id: "qwen-3-235b-a22b-instruct-2507",
        name: "Qwen 3 235B Instruct",
        api: Api::OpenAiCompletions,
        provider: "cerebras",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "zai-glm-4.7",
        name: "Z.AI GLM-4.7",
        api: Api::OpenAiCompletions,
        provider: "cerebras",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 40000,
    },
];

/// cloudflare-ai-gateway models (20 entries)
static CLOUDFLARE_AI_GATEWAY_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "claude-3-5-haiku",
        name: "Claude Haiku 3.5 (latest)",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 1.0,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "claude-3-haiku",
        name: "Claude Haiku 3",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.3,
        context_window: 200000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "claude-3-sonnet",
        name: "Claude Sonnet 3",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 0.3,
        context_window: 200000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "claude-3.5-sonnet",
        name: "Claude Sonnet 3.5 v2",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "claude-opus-4",
        name: "Claude Opus 4 (latest)",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-1",
        name: "Claude Opus 4.1 (latest)",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-6",
        name: "Claude Opus 4.6 (latest)",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "claude-sonnet-4",
        name: "Claude Sonnet 4 (latest)",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-6",
        name: "Claude Sonnet 4.6",
        api: Api::AnthropicMessages,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gpt-4",
        name: "GPT-4",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gpt-4o",
        name: "GPT-4o",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.1",
        name: "GPT-5.1",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.13,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2",
        name: "GPT-5.2",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-codex",
        name: "GPT-5.2 Codex",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4",
        name: "GPT-5.4",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.25,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "o1",
        name: "o1",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 7.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-mini",
        name: "o3-mini",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.55,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-pro",
        name: "o3-pro",
        api: Api::OpenAiResponses,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "workers-ai/@cf/moonshotai/kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "workers-ai/@cf/nvidia/nemotron-3-120b-a12b",
        name: "Nemotron 3 Super 120B",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
];

/// cloudflare-workers-ai models (8 entries)
static CLOUDFLARE_WORKERS_AI_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "@cf/google/gemma-4-26b-a4b-it",
        name: "Gemma 4 26B A4B IT",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "@cf/meta/llama-4-scout-17b-16e-instruct",
        name: "Llama 4 Scout 17B 16E Instruct",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "@cf/moonshotai/kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "@cf/moonshotai/kimi-k2.6",
        name: "Kimi K2.6",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.16,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "@cf/nvidia/nemotron-3-120b-a12b",
        name: "Nemotron 3 Super 120B",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "@cf/openai/gpt-oss-120b",
        name: "GPT OSS 120B",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "@cf/openai/gpt-oss-20b",
        name: "GPT OSS 20B",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "@cf/zai-org/glm-4.7-flash",
        name: "GLM-4.7-Flash",
        api: Api::OpenAiCompletions,
        provider: "cloudflare-workers-ai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
];

/// deepseek models (2 entries)
static DEEPSEEK_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "deepseek-v4-flash",
        name: "DeepSeek V4 Flash",
        api: Api::OpenAiCompletions,
        provider: "deepseek",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0028,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 384000,
    },
    ModelEntry {
        id: "deepseek-v4-pro",
        name: "DeepSeek V4 Pro",
        api: Api::OpenAiCompletions,
        provider: "deepseek",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.003625,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 384000,
    },
];

/// fireworks models (19 entries)
static FIREWORKS_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "accounts/fireworks/models/deepseek-v3p1",
        name: "DeepSeek V3.1",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 163840,
        max_tokens: 163840,
    },
    ModelEntry {
        id: "accounts/fireworks/models/deepseek-v3p2",
        name: "DeepSeek V3.2",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.28,
        cost_cache_write: 0.0,
        context_window: 160000,
        max_tokens: 160000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/deepseek-v4-pro",
        name: "DeepSeek V4 Pro",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 384000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/glm-4p5",
        name: "GLM 4.5",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "accounts/fireworks/models/glm-4p5-air",
        name: "GLM 4.5 Air",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "accounts/fireworks/models/glm-4p7",
        name: "GLM 4.7",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 0.0,
        context_window: 198000,
        max_tokens: 198000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/glm-5",
        name: "GLM 5",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "accounts/fireworks/models/glm-5p1",
        name: "GLM 5.1",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.26,
        cost_cache_write: 0.0,
        context_window: 202800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "accounts/fireworks/models/gpt-oss-120b",
        name: "GPT OSS 120B",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "accounts/fireworks/models/gpt-oss-20b",
        name: "GPT OSS 20B",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "accounts/fireworks/models/kimi-k2-instruct",
        name: "Kimi K2 Instruct",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "accounts/fireworks/models/kimi-k2-thinking",
        name: "Kimi K2 Thinking",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/kimi-k2p5",
        name: "Kimi K2.5",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/kimi-k2p6",
        name: "Kimi K2.6",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.16,
        cost_cache_write: 0.0,
        context_window: 262000,
        max_tokens: 262000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/minimax-m2p1",
        name: "MiniMax-M2.1",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 200000,
    },
    ModelEntry {
        id: "accounts/fireworks/models/minimax-m2p5",
        name: "MiniMax-M2.5",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 196608,
        max_tokens: 196608,
    },
    ModelEntry {
        id: "accounts/fireworks/models/minimax-m2p7",
        name: "MiniMax-M2.7",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 196608,
        max_tokens: 196608,
    },
    ModelEntry {
        id: "accounts/fireworks/models/qwen3p6-plus",
        name: "Qwen 3.6 Plus",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "accounts/fireworks/routers/kimi-k2p5-turbo",
        name: "Kimi K2.5 Turbo",
        api: Api::AnthropicMessages,
        provider: "fireworks",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
];

/// github-copilot models (26 entries)
static GITHUB_COPILOT_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "claude-haiku-4.5",
        name: "Claude Haiku 4.5",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 144000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4.5",
        name: "Claude Opus 4.5",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 160000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4.6",
        name: "Claude Opus 4.6",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-opus-4.7",
        name: "Claude Opus 4.7",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 144000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4",
        name: "Claude Sonnet 4",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 216000,
        max_tokens: 16000,
    },
    ModelEntry {
        id: "claude-sonnet-4.5",
        name: "Claude Sonnet 4.5",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 144000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-sonnet-4.6",
        name: "Claude Sonnet 4.6",
        api: Api::AnthropicMessages,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "gemini-2.5-pro",
        name: "Gemini 2.5 Pro",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gemini-3-flash-preview",
        name: "Gemini 3 Flash",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gemini-3-pro-preview",
        name: "Gemini 3 Pro Preview",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gemini-3.1-pro-preview",
        name: "Gemini 3.1 Pro Preview",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gpt-4.1",
        name: "GPT-4.1",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o",
        name: "GPT-4o",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "gpt-5",
        name: "GPT-5",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-mini",
        name: "GPT-5-mini",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 264000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gpt-5.1",
        name: "GPT-5.1",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 264000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gpt-5.1-codex",
        name: "GPT-5.1-Codex",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-max",
        name: "GPT-5.1-Codex-max",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-mini",
        name: "GPT-5.1-Codex-mini",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2",
        name: "GPT-5.2",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 264000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gpt-5.2-codex",
        name: "GPT-5.2-Codex",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-codex",
        name: "GPT-5.3-Codex",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4",
        name: "GPT-5.4",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-mini",
        name: "GPT-5.4 Mini",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5",
        name: "GPT-5.5",
        api: Api::OpenAiResponses,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "grok-code-fast-1",
        name: "Grok Code Fast 1",
        api: Api::OpenAiCompletions,
        provider: "github-copilot",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 64000,
    },
];

/// google models (27 entries)
static GOOGLE_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "gemini-1.5-flash",
        name: "Gemini 1.5 Flash",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01875,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-1.5-flash-8b",
        name: "Gemini 1.5 Flash-8B",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-1.5-pro",
        name: "Gemini 1.5 Pro",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3125,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-2.0-flash",
        name: "Gemini 2.0 Flash",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-2.0-flash-lite",
        name: "Gemini 2.0 Flash Lite",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-2.5-flash",
        name: "Gemini 2.5 Flash",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-lite",
        name: "Gemini 2.5 Flash Lite",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-lite-preview-06-17",
        name: "Gemini 2.5 Flash Lite Preview 06-17",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-lite-preview-09-2025",
        name: "Gemini 2.5 Flash Lite Preview 09-25",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-preview-04-17",
        name: "Gemini 2.5 Flash Preview 04-17",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0375,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-preview-05-20",
        name: "Gemini 2.5 Flash Preview 05-20",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0375,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-preview-09-2025",
        name: "Gemini 2.5 Flash Preview 09-25",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-pro",
        name: "Gemini 2.5 Pro",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-pro-preview-05-06",
        name: "Gemini 2.5 Pro Preview 05-06",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.31,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-pro-preview-06-05",
        name: "Gemini 2.5 Pro Preview 06-05",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.31,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3-flash-preview",
        name: "Gemini 3 Flash Preview",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3-pro-preview",
        name: "Gemini 3 Pro Preview",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gemini-3.1-flash-lite-preview",
        name: "Gemini 3.1 Flash Lite Preview",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 1.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3.1-pro-preview",
        name: "Gemini 3.1 Pro Preview",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3.1-pro-preview-customtools",
        name: "Gemini 3.1 Pro Preview Custom Tools",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-flash-latest",
        name: "Gemini Flash Latest",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-flash-lite-latest",
        name: "Gemini Flash-Lite Latest",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-live-2.5-flash",
        name: "Gemini Live 2.5 Flash",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 8000,
    },
    ModelEntry {
        id: "gemini-live-2.5-flash-preview-native-audio",
        name: "Gemini Live 2.5 Flash Preview Native Audio",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemma-3-27b-it",
        name: "Gemma 3 27B",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemma-4-26b-a4b-it",
        name: "Gemma 4 26B",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemma-4-31b-it",
        name: "Gemma 4 31B",
        api: Api::GoogleGenerativeAi,
        provider: "google",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 8192,
    },
];

/// google-vertex models (13 entries)
static GOOGLE_VERTEX_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "gemini-1.5-flash",
        name: "Gemini 1.5 Flash (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01875,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-1.5-flash-8b",
        name: "Gemini 1.5 Flash-8B (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-1.5-pro",
        name: "Gemini 1.5 Pro (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3125,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-2.0-flash",
        name: "Gemini 2.0 Flash (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0375,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemini-2.0-flash-lite",
        name: "Gemini 2.0 Flash Lite (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01875,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash",
        name: "Gemini 2.5 Flash (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-lite",
        name: "Gemini 2.5 Flash Lite (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-flash-lite-preview-09-2025",
        name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-2.5-pro",
        name: "Gemini 2.5 Pro (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3-flash-preview",
        name: "Gemini 3 Flash Preview (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3-pro-preview",
        name: "Gemini 3 Pro Preview (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gemini-3.1-pro-preview",
        name: "Gemini 3.1 Pro Preview (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "gemini-3.1-pro-preview-customtools",
        name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
        api: Api::GoogleVertex,
        provider: "google-vertex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
];

/// groq models (18 entries)
static GROQ_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "deepseek-r1-distill-llama-70b",
        name: "DeepSeek R1 Distill Llama 70B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gemma2-9b-it",
        name: "Gemma 2 9B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "groq/compound",
        name: "Compound",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "groq/compound-mini",
        name: "Compound Mini",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "llama-3.1-8b-instant",
        name: "Llama 3.1 8B Instant",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "llama-3.3-70b-versatile",
        name: "Llama 3.3 70B Versatile",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "llama3-70b-8192",
        name: "Llama 3 70B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "llama3-8b-8192",
        name: "Llama 3 8B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "meta-llama/llama-4-maverick-17b-128e-instruct",
        name: "Llama 4 Maverick 17B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "meta-llama/llama-4-scout-17b-16e-instruct",
        name: "Llama 4 Scout 17B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "mistral-saba-24b",
        name: "Mistral Saba 24B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 32768,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "moonshotai/kimi-k2-instruct",
        name: "Kimi K2 Instruct",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "moonshotai/kimi-k2-instruct-0905",
        name: "Kimi K2 Instruct 0905",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "openai/gpt-oss-120b",
        name: "GPT OSS 120B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "openai/gpt-oss-20b",
        name: "GPT OSS 20B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "openai/gpt-oss-safeguard-20b",
        name: "Safety GPT OSS 20B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.037,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "qwen-qwq-32b",
        name: "Qwen QwQ 32B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "qwen/qwen3-32b",
        name: "Qwen3 32B",
        api: Api::OpenAiCompletions,
        provider: "groq",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 40960,
    },
];

/// huggingface models (22 entries)
static HUGGINGFACE_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "MiniMaxAI/MiniMax-M2.1",
        name: "MiniMax-M2.1",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "MiniMaxAI/MiniMax-M2.5",
        name: "MiniMax-M2.5",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "MiniMaxAI/MiniMax-M2.7",
        name: "MiniMax-M2.7",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
        name: "Qwen3-235B-A22B-Thinking-2507",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
        name: "Qwen3-Coder-480B-A35B-Instruct",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 66536,
    },
    ModelEntry {
        id: "Qwen/Qwen3-Coder-Next",
        name: "Qwen3-Coder-Next",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "Qwen/Qwen3-Next-80B-A3B-Instruct",
        name: "Qwen3-Next-80B-A3B-Instruct",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 66536,
    },
    ModelEntry {
        id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
        name: "Qwen3-Next-80B-A3B-Thinking",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "Qwen/Qwen3.5-397B-A17B",
        name: "Qwen3.5-397B-A17B",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "XiaomiMiMo/MiMo-V2-Flash",
        name: "MiMo-V2-Flash",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "deepseek-ai/DeepSeek-R1-0528",
        name: "DeepSeek-R1-0528",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 163840,
        max_tokens: 163840,
    },
    ModelEntry {
        id: "deepseek-ai/DeepSeek-V3.2",
        name: "DeepSeek-V3.2",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 163840,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "deepseek-ai/DeepSeek-V4-Pro",
        name: "DeepSeek V4 Pro",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.145,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 393216,
    },
    ModelEntry {
        id: "moonshotai/Kimi-K2-Instruct",
        name: "Kimi-K2-Instruct",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "moonshotai/Kimi-K2-Instruct-0905",
        name: "Kimi-K2-Instruct-0905",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "moonshotai/Kimi-K2-Thinking",
        name: "Kimi-K2-Thinking",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "moonshotai/Kimi-K2.5",
        name: "Kimi-K2.5",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "moonshotai/Kimi-K2.6",
        name: "Kimi-K2.6",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.16,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "zai-org/GLM-4.7",
        name: "GLM-4.7",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.11,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "zai-org/GLM-4.7-Flash",
        name: "GLM-4.7-Flash",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "zai-org/GLM-5",
        name: "GLM-5",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "zai-org/GLM-5.1",
        name: "GLM-5.1",
        api: Api::OpenAiCompletions,
        provider: "huggingface",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 131072,
    },
];

/// kimi-coding models (3 entries)
static KIMI_CODING_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "k2p6",
        name: "Kimi K2.6",
        api: Api::AnthropicMessages,
        provider: "kimi-coding",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "kimi-for-coding",
        name: "Kimi For Coding",
        api: Api::AnthropicMessages,
        provider: "kimi-coding",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "kimi-k2-thinking",
        name: "Kimi K2 Thinking",
        api: Api::AnthropicMessages,
        provider: "kimi-coding",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
];

/// minimax models (2 entries)
static MINIMAX_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "MiniMax-M2.7",
        name: "MiniMax-M2.7",
        api: Api::AnthropicMessages,
        provider: "minimax",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.375,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "MiniMax-M2.7-highspeed",
        name: "MiniMax-M2.7-highspeed",
        api: Api::AnthropicMessages,
        provider: "minimax",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.375,
        context_window: 204800,
        max_tokens: 131072,
    },
];

/// minimax-cn models (2 entries)
static MINIMAX_CN_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "MiniMax-M2.7",
        name: "MiniMax-M2.7",
        api: Api::AnthropicMessages,
        provider: "minimax-cn",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.375,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "MiniMax-M2.7-highspeed",
        name: "MiniMax-M2.7-highspeed",
        api: Api::AnthropicMessages,
        provider: "minimax-cn",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.375,
        context_window: 204800,
        max_tokens: 131072,
    },
];

/// mistral models (28 entries)
static MISTRAL_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "codestral-latest",
        name: "Codestral (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "devstral-2512",
        name: "Devstral 2",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "devstral-medium-2507",
        name: "Devstral Medium",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "devstral-medium-latest",
        name: "Devstral 2 (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "devstral-small-2505",
        name: "Devstral Small 2505",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "devstral-small-2507",
        name: "Devstral Small",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "labs-devstral-small-2512",
        name: "Devstral Small 2",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "magistral-medium-latest",
        name: "Magistral Medium (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "magistral-small",
        name: "Magistral Small",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "ministral-3b-latest",
        name: "Ministral 3B (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "ministral-8b-latest",
        name: "Ministral 8B (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mistral-large-2411",
        name: "Mistral Large 2.1",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "mistral-large-2512",
        name: "Mistral Large 3",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "mistral-large-latest",
        name: "Mistral Large (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "mistral-medium-2505",
        name: "Mistral Medium 3",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "mistral-medium-2508",
        name: "Mistral Medium 3.1",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "mistral-medium-2604",
        name: "Mistral Medium 3.5",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "mistral-medium-3.5",
        name: "Mistral Medium 3.5",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "mistral-medium-latest",
        name: "Mistral Medium (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "mistral-nemo",
        name: "Mistral Nemo",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mistral-small-2506",
        name: "Mistral Small 3.2",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "mistral-small-2603",
        name: "Mistral Small 4",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "mistral-small-latest",
        name: "Mistral Small (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "open-mistral-7b",
        name: "Mistral 7B",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8000,
        max_tokens: 8000,
    },
    ModelEntry {
        id: "open-mixtral-8x22b",
        name: "Mixtral 8x22B",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 64000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "open-mixtral-8x7b",
        name: "Mixtral 8x7B",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 32000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "pixtral-12b",
        name: "Pixtral 12B",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "pixtral-large-latest",
        name: "Pixtral Large (latest)",
        api: Api::MistralConversations,
        provider: "mistral",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
];

/// moonshotai models (7 entries)
static MOONSHOTAI_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "kimi-k2-0711-preview",
        name: "Kimi K2 0711",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "kimi-k2-0905-preview",
        name: "Kimi K2 0905",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2-thinking",
        name: "Kimi K2 Thinking",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2-thinking-turbo",
        name: "Kimi K2 Thinking Turbo",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2-turbo-preview",
        name: "Kimi K2 Turbo",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.6,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2.6",
        name: "Kimi K2.6",
        api: Api::OpenAiCompletions,
        provider: "moonshotai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.16,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
];

/// moonshotai-cn models (7 entries)
static MOONSHOTAI_CN_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "kimi-k2-0711-preview",
        name: "Kimi K2 0711",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "kimi-k2-0905-preview",
        name: "Kimi K2 0905",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2-thinking",
        name: "Kimi K2 Thinking",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2-thinking-turbo",
        name: "Kimi K2 Thinking Turbo",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2-turbo-preview",
        name: "Kimi K2 Turbo",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.6,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "kimi-k2.6",
        name: "Kimi K2.6",
        api: Api::OpenAiCompletions,
        provider: "moonshotai-cn",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.16,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
];

/// openai models (42 entries)
static OPENAI_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "gpt-4",
        name: "GPT-4",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "gpt-4-turbo",
        name: "GPT-4 Turbo",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "gpt-4.1",
        name: "GPT-4.1",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "gpt-4.1-mini",
        name: "GPT-4.1 mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "gpt-4.1-nano",
        name: "GPT-4.1 nano",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "gpt-4o",
        name: "GPT-4o",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o-2024-05-13",
        name: "GPT-4o (2024-05-13)",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "gpt-4o-2024-08-06",
        name: "GPT-4o (2024-08-06)",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o-2024-11-20",
        name: "GPT-4o (2024-11-20)",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-4o-mini",
        name: "GPT-4o mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5",
        name: "GPT-5",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-chat-latest",
        name: "GPT-5 Chat Latest",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5-codex",
        name: "GPT-5-Codex",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-mini",
        name: "GPT-5 Mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-nano",
        name: "GPT-5 Nano",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.005,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-pro",
        name: "GPT-5 Pro",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 272000,
    },
    ModelEntry {
        id: "gpt-5.1",
        name: "GPT-5.1",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.13,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-chat-latest",
        name: "GPT-5.1 Chat",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.1-codex",
        name: "GPT-5.1 Codex",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-max",
        name: "GPT-5.1 Codex Max",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-mini",
        name: "GPT-5.1 Codex mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2",
        name: "GPT-5.2",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-chat-latest",
        name: "GPT-5.2 Chat",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.2-codex",
        name: "GPT-5.2 Codex",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-pro",
        name: "GPT-5.2 Pro",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-chat-latest",
        name: "GPT-5.3 Chat (latest)",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "gpt-5.3-codex",
        name: "GPT-5.3 Codex",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-codex-spark",
        name: "GPT-5.3 Codex Spark",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "gpt-5.4",
        name: "GPT-5.4",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.25,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-mini",
        name: "GPT-5.4 mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-nano",
        name: "GPT-5.4 nano",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-pro",
        name: "GPT-5.4 Pro",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5",
        name: "GPT-5.5",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5-pro",
        name: "GPT-5.5 Pro",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "o1",
        name: "o1",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 7.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o1-pro",
        name: "o1-pro",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3",
        name: "o3",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-deep-research",
        name: "o3-deep-research",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-mini",
        name: "o3-mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.55,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o3-pro",
        name: "o3-pro",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o4-mini",
        name: "o4-mini",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.28,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "o4-mini-deep-research",
        name: "o4-mini-deep-research",
        api: Api::OpenAiResponses,
        provider: "openai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
];

/// openai-codex models (10 entries)
static OPENAI_CODEX_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "gpt-5.1",
        name: "GPT-5.1",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-max",
        name: "GPT-5.1 Codex Max",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-mini",
        name: "GPT-5.1 Codex Mini",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2",
        name: "GPT-5.2",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-codex",
        name: "GPT-5.2 Codex",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-codex",
        name: "GPT-5.3 Codex",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-codex-spark",
        name: "GPT-5.3 Codex Spark",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4",
        name: "GPT-5.4",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.25,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-mini",
        name: "GPT-5.4 Mini",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5",
        name: "GPT-5.5",
        api: Api::OpenAiCompletions,
        provider: "openai-codex",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 272000,
        max_tokens: 128000,
    },
];

/// opencode models (30 entries)
static OPENCODE_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "big-pickle",
        name: "Big Pickle",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "claude-haiku-4-5",
        name: "Claude Haiku 4.5",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-opus-4-1",
        name: "Claude Opus 4.1",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "claude-opus-4-5",
        name: "Claude Opus 4.5",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-opus-4-7",
        name: "Claude Opus 4.7",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "claude-sonnet-4",
        name: "Claude Sonnet 4",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-5",
        name: "Claude Sonnet 4.5",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "claude-sonnet-4-6",
        name: "Claude Sonnet 4.6",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "gemini-3.1-pro",
        name: "Gemini 3.1 Pro Preview",
        api: Api::GoogleGenerativeAi,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "glm-5",
        name: "GLM-5",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "glm-5.1",
        name: "GLM-5.1",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.26,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "gpt-5",
        name: "GPT-5",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.107,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5-nano",
        name: "GPT-5 Nano",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1",
        name: "GPT-5.1",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.107,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex",
        name: "GPT-5.1 Codex",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.107,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.1-codex-mini",
        name: "GPT-5.1 Codex Mini",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.025,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2",
        name: "GPT-5.2",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.2-codex",
        name: "GPT-5.2 Codex",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.3-codex",
        name: "GPT-5.3 Codex",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-mini",
        name: "GPT-5.4 Mini",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-nano",
        name: "GPT-5.4 Nano",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.4-pro",
        name: "GPT-5.4 Pro",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 30.0,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "gpt-5.5",
        name: "GPT-5.5",
        api: Api::OpenAiResponses,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 1050000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "hy3-preview-free",
        name: "Hy3 preview Free",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "kimi-k2.6",
        name: "Kimi K2.6",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.16,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "minimax-m2.5",
        name: "MiniMax M2.5",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "minimax-m2.7",
        name: "MiniMax M2.7",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "nemotron-3-super-free",
        name: "Nemotron 3 Super Free",
        api: Api::OpenAiCompletions,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "qwen3.5-plus",
        name: "Qwen3.5 Plus",
        api: Api::AnthropicMessages,
        provider: "opencode",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.25,
        context_window: 262144,
        max_tokens: 65536,
    },
];

/// opencode-go models (14 entries)
static OPENCODE_GO_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "deepseek-v4-flash",
        name: "DeepSeek V4 Flash",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0028,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 384000,
    },
    ModelEntry {
        id: "deepseek-v4-pro",
        name: "DeepSeek V4 Pro",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0145,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 384000,
    },
    ModelEntry {
        id: "glm-5",
        name: "GLM-5",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "glm-5.1",
        name: "GLM-5.1",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.26,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.1,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "kimi-k2.6",
        name: "Kimi K2.6 (3x limits)",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.054,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "mimo-v2-omni",
        name: "MiMo V2 Omni",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mimo-v2-pro",
        name: "MiMo V2 Pro",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mimo-v2.5",
        name: "MiMo V2.5",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mimo-v2.5-pro",
        name: "MiMo V2.5 Pro",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "minimax-m2.5",
        name: "MiniMax M2.5",
        api: Api::OpenAiCompletions,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "minimax-m2.7",
        name: "MiniMax M2.7",
        api: Api::AnthropicMessages,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "qwen3.5-plus",
        name: "Qwen3.5 Plus",
        api: Api::AnthropicMessages,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.25,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "qwen3.6-plus",
        name: "Qwen3.6 Plus",
        api: Api::AnthropicMessages,
        provider: "opencode-go",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.625,
        context_window: 262144,
        max_tokens: 65536,
    },
];

/// openrouter models (60 entries)
static OPENROUTER_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "ai21/jamba-large-1.7",
        name: "AI21: Jamba Large 1.7",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "amazon/nova-lite-v1",
        name: "Amazon: Nova Lite 1.0",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 300000,
        max_tokens: 5120,
    },
    ModelEntry {
        id: "anthropic/claude-3.5-haiku",
        name: "Anthropic: Claude 3.5 Haiku",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 1.0,
        context_window: 200000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "anthropic/claude-opus-4",
        name: "Anthropic: Claude Opus 4",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.5,
        cost_cache_write: 18.75,
        context_window: 200000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "anthropic/claude-opus-4.7",
        name: "Anthropic: Claude Opus 4.7",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 6.25,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "arcee-ai/trinity-large-preview",
        name: "Arcee AI: Trinity Large Preview",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "baidu/ernie-4.5-21b-a3b",
        name: "Baidu: ERNIE 4.5 21B A3B",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 120000,
        max_tokens: 8000,
    },
    ModelEntry {
        id: "bytedance-seed/seed-2.0-lite",
        name: "ByteDance Seed: Seed-2.0-Lite",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "deepseek/deepseek-chat-v3-0324",
        name: "DeepSeek: DeepSeek V3 0324",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.135,
        cost_cache_write: 0.0,
        context_window: 163840,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "deepseek/deepseek-v3.1-terminus",
        name: "DeepSeek: DeepSeek V3.1 Terminus",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.13,
        cost_cache_write: 0.0,
        context_window: 163840,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "essentialai/rnj-1-instruct",
        name: "EssentialAI: Rnj 1 Instruct",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 32768,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "google/gemini-2.5-flash-lite-preview-09-2025",
        name: "Google: Gemini 2.5 Flash Lite Preview 09-2025",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.08333333333333334,
        context_window: 1048576,
        max_tokens: 65535,
    },
    ModelEntry {
        id: "google/gemini-3-flash-preview",
        name: "Google: Gemini 3 Flash Preview",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.049999999999999996,
        cost_cache_write: 0.08333333333333334,
        context_window: 1048576,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "google/gemma-3-27b-it",
        name: "Google: Gemma 3 27B",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "google/gemma-4-31b-it:free",
        name: "Google: Gemma 4 31B (free)",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "kwaipilot/kat-coder-pro-v2",
        name: "Kwaipilot: KAT-Coder-Pro V2",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 80000,
    },
    ModelEntry {
        id: "meta-llama/llama-3.3-70b-instruct",
        name: "Meta: Llama 3.3 70B Instruct",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "minimax/minimax-m2.1",
        name: "MiniMax: MiniMax M2.1",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 196608,
        max_tokens: 196608,
    },
    ModelEntry {
        id: "mistralai/codestral-2508",
        name: "Mistral: Codestral 2508",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "mistralai/ministral-3b-2512",
        name: "Mistral: Ministral 3 3B 2512",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "mistralai/mistral-large-2512",
        name: "Mistral: Mistral Large 3 2512",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.049999999999999996,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "mistralai/mistral-saba",
        name: "Mistral: Saba",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 32768,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "mistralai/pixtral-large-2411",
        name: "Mistral: Pixtral Large 2411",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.19999999999999998,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "moonshotai/kimi-k2-thinking",
        name: "MoonshotAI: Kimi K2 Thinking",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
        name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "nvidia/nemotron-3-super-120b-a12b",
        name: "NVIDIA: Nemotron 3 Super",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "openai/gpt-3.5-turbo",
        name: "OpenAI: GPT-3.5 Turbo",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 16385,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "openai/gpt-4-0314",
        name: "OpenAI: GPT-4 (older v0314)",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 8191,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "openai/gpt-4.1-mini",
        name: "OpenAI: GPT-4.1 Mini",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.09999999999999999,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "openai/gpt-4o-2024-08-06",
        name: "OpenAI: GPT-4o (2024-08-06)",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "openai/gpt-5",
        name: "OpenAI: GPT-5",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "openai/gpt-5.1",
        name: "OpenAI: GPT-5.1",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.13,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "openai/gpt-5.1-codex-mini",
        name: "OpenAI: GPT-5.1-Codex-Mini",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "openai/gpt-5.3-chat",
        name: "OpenAI: GPT-5.3 Chat",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "openai/gpt-5.4-nano",
        name: "OpenAI: GPT-5.4 Nano",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "openai/gpt-audio-mini",
        name: "OpenAI: GPT Audio Mini",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "openai/gpt-oss-20b:free",
        name: "OpenAI: gpt-oss-20b (free)",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "openai/o3-mini",
        name: "OpenAI: o3 Mini",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.55,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "openai/o4-mini-deep-research",
        name: "OpenAI: o4 Mini Deep Research",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "poolside/laguna-m.1:free",
        name: "Poolside: Laguna M.1 (free)",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "qwen/qwen-max",
        name: "Qwen: Qwen-Max ",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.20800000000000002,
        cost_cache_write: 0.0,
        context_window: 32768,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "qwen/qwen-turbo",
        name: "Qwen: Qwen-Turbo",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.006500000000000001,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "qwen/qwen3-235b-a22b-thinking-2507",
        name: "Qwen: Qwen3 235B A22B Thinking 2507",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "qwen/qwen3-32b",
        name: "Qwen: Qwen3 32B",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.04,
        cost_cache_write: 0.0,
        context_window: 40960,
        max_tokens: 40960,
    },
    ModelEntry {
        id: "qwen/qwen3-coder-next",
        name: "Qwen: Qwen3 Coder Next",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.07,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "qwen/qwen3-max-thinking",
        name: "Qwen: Qwen3 Max Thinking",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "qwen/qwen3-vl-235b-a22b-thinking",
        name: "Qwen: Qwen3 VL 235B A22B Thinking",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "qwen/qwen3-vl-8b-instruct",
        name: "Qwen: Qwen3 VL 8B Instruct",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "qwen/qwen3.5-397b-a17b",
        name: "Qwen: Qwen3.5 397B A17B",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.195,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "qwen/qwen3.5-plus-20260420",
        name: "Qwen: Qwen3.5 Plus 2026-04-20",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 65536,
    },
    ModelEntry {
        id: "rekaai/reka-edge",
        name: "Reka Edge",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 16384,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "tencent/hy3-preview:free",
        name: "Tencent: Hy3 preview (free)",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 262144,
    },
    ModelEntry {
        id: "upstage/solar-pro-3",
        name: "Upstage: Solar Pro 3",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.015,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "x-ai/grok-4",
        name: "xAI: Grok 4",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.75,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "x-ai/grok-4.3",
        name: "xAI: Grok 4.3",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.19999999999999998,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "xiaomi/mimo-v2.5",
        name: "Xiaomi: MiMo-V2.5",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "z-ai/glm-4.5-air",
        name: "Z.ai: GLM 4.5 Air",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.024999999999999998,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 98304,
    },
    ModelEntry {
        id: "z-ai/glm-4.7",
        name: "Z.ai: GLM 4.7",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "z-ai/glm-5.1",
        name: "Z.ai: GLM 5.1",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.5249999999999999,
        cost_cache_write: 0.0,
        context_window: 202752,
        max_tokens: 65535,
    },
    ModelEntry {
        id: "~google/gemini-flash-latest",
        name: "Google Gemini Flash Latest",
        api: Api::OpenAiCompletions,
        provider: "openrouter",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.049999999999999996,
        cost_cache_write: 0.08333333333333334,
        context_window: 1048576,
        max_tokens: 65536,
    },
];

/// vercel-ai-gateway models (30 entries)
static VERCEL_AI_GATEWAY_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "alibaba/qwen-3-14b",
        name: "Qwen3-14B",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 40960,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "alibaba/qwen3-235b-a22b-thinking",
        name: "Qwen3 VL 235B A22B Thinking",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "alibaba/qwen3-max",
        name: "Qwen3 Max",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.24,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "alibaba/qwen3.6-27b",
        name: "Qwen 3.6 27B",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "anthropic/claude-haiku-4.5",
        name: "Claude Haiku 4.5",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.09999999999999999,
        cost_cache_write: 1.25,
        context_window: 200000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "anthropic/claude-sonnet-4",
        name: "Claude Sonnet 4",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.3,
        cost_cache_write: 3.75,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "bytedance/seed-1.6",
        name: "Seed 1.6",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.049999999999999996,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "deepseek/deepseek-v3.2",
        name: "DeepSeek V3.2",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.028,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 8000,
    },
    ModelEntry {
        id: "google/gemini-2.0-flash-lite",
        name: "Gemini 2.0 Flash Lite",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "google/gemini-3-pro-preview",
        name: "Gemini 3 Pro Preview",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.19999999999999998,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "inception/mercury-coder-small",
        name: "Mercury Coder Small Beta",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 32000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "meta/llama-3.2-11b",
        name: "Llama 3.2 11B Vision Instruct",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "minimax/minimax-m2.1",
        name: "MiniMax M2.1",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.03,
        cost_cache_write: 0.375,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "minimax/minimax-m2.7-highspeed",
        name: "MiniMax M2.7 High Speed",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.06,
        cost_cache_write: 0.375,
        context_window: 204800,
        max_tokens: 131100,
    },
    ModelEntry {
        id: "mistral/ministral-8b",
        name: "Ministral 8B",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 4000,
    },
    ModelEntry {
        id: "moonshotai/kimi-k2",
        name: "Kimi K2 Instruct",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "moonshotai/kimi-k2.5",
        name: "Kimi K2.5",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.09999999999999999,
        cost_cache_write: 0.0,
        context_window: 262114,
        max_tokens: 262114,
    },
    ModelEntry {
        id: "openai/gpt-4.1-mini",
        name: "GPT-4.1 mini",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.09999999999999999,
        cost_cache_write: 0.0,
        context_window: 1047576,
        max_tokens: 32768,
    },
    ModelEntry {
        id: "openai/gpt-5-chat",
        name: "GPT 5 Chat",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "openai/gpt-5.1-codex-max",
        name: "GPT 5.1 Codex Max",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.125,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "openai/gpt-5.2-chat",
        name: "GPT 5.2 Chat",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.175,
        cost_cache_write: 0.0,
        context_window: 128000,
        max_tokens: 16384,
    },
    ModelEntry {
        id: "openai/gpt-5.4-mini",
        name: "GPT 5.4 Mini",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 400000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "openai/gpt-oss-20b",
        name: "GPT OSS 120B",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "openai/o3-mini",
        name: "o3-mini",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.55,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 100000,
    },
    ModelEntry {
        id: "xai/grok-3-fast",
        name: "Grok 3 Fast Beta",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "xai/grok-4-fast-reasoning",
        name: "Grok 4 Fast Reasoning",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.049999999999999996,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 256000,
    },
    ModelEntry {
        id: "xai/grok-4.20-non-reasoning-beta",
        name: "Grok 4.20 Beta Non-Reasoning",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.19999999999999998,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 2000000,
    },
    ModelEntry {
        id: "xiaomi/mimo-v2-flash",
        name: "MiMo V2 Flash",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 262144,
        max_tokens: 32000,
    },
    ModelEntry {
        id: "zai/glm-4.5v",
        name: "GLM 4.5V",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.11,
        cost_cache_write: 0.0,
        context_window: 66000,
        max_tokens: 16000,
    },
    ModelEntry {
        id: "zai/glm-4.7-flash",
        name: "GLM 4.7 Flash",
        api: Api::AnthropicMessages,
        provider: "vercel-ai-gateway",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 131000,
    },
];

/// xai models (25 entries)
static XAI_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "grok-2",
        name: "Grok 2",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-2-1212",
        name: "Grok 2 (1212)",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-2-latest",
        name: "Grok 2 Latest",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-2-vision",
        name: "Grok 2 Vision",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "grok-2-vision-1212",
        name: "Grok 2 Vision (1212)",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "grok-2-vision-latest",
        name: "Grok 2 Vision Latest",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 2.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "grok-3",
        name: "Grok 3",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.75,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-fast",
        name: "Grok 3 Fast",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-fast-latest",
        name: "Grok 3 Fast Latest",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 1.25,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-latest",
        name: "Grok 3 Latest",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.75,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-mini",
        name: "Grok 3 Mini",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-mini-fast",
        name: "Grok 3 Mini Fast",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-mini-fast-latest",
        name: "Grok 3 Mini Fast Latest",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.15,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-3-mini-latest",
        name: "Grok 3 Mini Latest",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.075,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 8192,
    },
    ModelEntry {
        id: "grok-4",
        name: "Grok 4",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.75,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "grok-4-1-fast",
        name: "Grok 4.1 Fast",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-4-1-fast-non-reasoning",
        name: "Grok 4.1 Fast (Non-Reasoning)",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-4-fast",
        name: "Grok 4 Fast",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-4-fast-non-reasoning",
        name: "Grok 4 Fast (Non-Reasoning)",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.05,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-4.20-0309-non-reasoning",
        name: "Grok 4.20 (Non-Reasoning)",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-4.20-0309-reasoning",
        name: "Grok 4.20 (Reasoning)",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 2000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-4.3",
        name: "Grok 4.3",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 30000,
    },
    ModelEntry {
        id: "grok-beta",
        name: "Grok Beta",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 5.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 4096,
    },
    ModelEntry {
        id: "grok-code-fast-1",
        name: "Grok Code Fast 1",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.02,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 10000,
    },
    ModelEntry {
        id: "grok-vision-beta",
        name: "Grok Vision Beta",
        api: Api::OpenAiCompletions,
        provider: "xai",
        reasoning: false,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 5.0,
        cost_cache_write: 0.0,
        context_window: 8192,
        max_tokens: 4096,
    },
];

/// xiaomi models (5 entries)
static XIAOMI_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "mimo-v2-flash",
        name: "MiMo-V2-Flash",
        api: Api::AnthropicMessages,
        provider: "xiaomi",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.01,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 64000,
    },
    ModelEntry {
        id: "mimo-v2-omni",
        name: "MiMo-V2-Omni",
        api: Api::AnthropicMessages,
        provider: "xiaomi",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 256000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mimo-v2-pro",
        name: "MiMo-V2-Pro",
        api: Api::AnthropicMessages,
        provider: "xiaomi",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1000000,
        max_tokens: 128000,
    },
    ModelEntry {
        id: "mimo-v2.5",
        name: "MiMo-V2.5",
        api: Api::AnthropicMessages,
        provider: "xiaomi",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.08,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "mimo-v2.5-pro",
        name: "MiMo-V2.5-Pro",
        api: Api::AnthropicMessages,
        provider: "xiaomi",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.2,
        cost_cache_write: 0.0,
        context_window: 1048576,
        max_tokens: 131072,
    },
];

/// zai models (5 entries)
static ZAI_MODELS: &[ModelEntry] = &[
    ModelEntry {
        id: "glm-4.5-air",
        name: "GLM-4.5-Air",
        api: Api::OpenAiCompletions,
        provider: "zai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 131072,
        max_tokens: 98304,
    },
    ModelEntry {
        id: "glm-4.7",
        name: "GLM-4.7",
        api: Api::OpenAiCompletions,
        provider: "zai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 204800,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "glm-5-turbo",
        name: "GLM-5-Turbo",
        api: Api::OpenAiCompletions,
        provider: "zai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "glm-5.1",
        name: "GLM-5.1",
        api: Api::OpenAiCompletions,
        provider: "zai",
        reasoning: true,
        input: &[InputModality::Text],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 131072,
    },
    ModelEntry {
        id: "glm-5v-turbo",
        name: "glm-5v-turbo",
        api: Api::OpenAiCompletions,
        provider: "zai",
        reasoning: true,
        input: &[InputModality::Text, InputModality::Image],
        cost_input: 0.0,
        cost_output: 0.0,
        cost_cache_read: 0.0,
        cost_cache_write: 0.0,
        context_window: 200000,
        max_tokens: 131072,
    },
];

/// All model arrays indexed by provider
static ALL_PROVIDER_MODELS: &[(&str, &[ModelEntry])] = &[
    ("amazon-bedrock", AMAZON_BEDROCK_MODELS),
    ("anthropic", ANTHROPIC_MODELS),
    ("azure-openai-responses", AZURE_OPENAI_RESPONSES_MODELS),
    ("cerebras", CEREBRAS_MODELS),
    ("cloudflare-ai-gateway", CLOUDFLARE_AI_GATEWAY_MODELS),
    ("cloudflare-workers-ai", CLOUDFLARE_WORKERS_AI_MODELS),
    ("deepseek", DEEPSEEK_MODELS),
    ("fireworks", FIREWORKS_MODELS),
    ("github-copilot", GITHUB_COPILOT_MODELS),
    ("google", GOOGLE_MODELS),
    ("google-vertex", GOOGLE_VERTEX_MODELS),
    ("groq", GROQ_MODELS),
    ("huggingface", HUGGINGFACE_MODELS),
    ("kimi-coding", KIMI_CODING_MODELS),
    ("minimax", MINIMAX_MODELS),
    ("minimax-cn", MINIMAX_CN_MODELS),
    ("mistral", MISTRAL_MODELS),
    ("moonshotai", MOONSHOTAI_MODELS),
    ("moonshotai-cn", MOONSHOTAI_CN_MODELS),
    ("openai", OPENAI_MODELS),
    ("openai-codex", OPENAI_CODEX_MODELS),
    ("opencode", OPENCODE_MODELS),
    ("opencode-go", OPENCODE_GO_MODELS),
    ("openrouter", OPENROUTER_MODELS),
    ("vercel-ai-gateway", VERCEL_AI_GATEWAY_MODELS),
    ("xai", XAI_MODELS),
    ("xiaomi", XIAOMI_MODELS),
    ("zai", ZAI_MODELS),
];

/// Look up a specific model entry by provider and model ID.
///
/// # Arguments
/// * `provider` - The provider name (e.g., "anthropic", "openai")
/// * `id` - The model ID (e.g., "claude-sonnet-4-20250514")
///
/// # Returns
/// `Some(&ModelEntry)` if found, `None` otherwise.
///
/// # Example
/// ```ignore
/// use oxi_ai::model_db::get_model_entry;
/// let m = get_model_entry("openai", "gpt-4o").unwrap();
/// assert_eq!(m.name, "GPT-4o");
/// ```
pub fn get_model_entry(provider: &str, id: &str) -> Option<&'static ModelEntry> {
    for (prov, models) in ALL_PROVIDER_MODELS.iter() {
        if *prov == provider {
            return models.iter().find(|m| m.id == id);
        }
    }
    None
}

/// Get all model entries for a given provider.
///
/// # Arguments
/// * `provider` - The provider name (e.g., "anthropic", "openai")
///
/// # Returns
/// A slice of `ModelEntry` for the provider, or an empty slice if not found.
pub fn get_provider_models(provider: &str) -> &'static [ModelEntry] {
    for (prov, models) in ALL_PROVIDER_MODELS.iter() {
        if *prov == provider {
            return models;
        }
    }
    &[]
}

/// Get all model entries across all providers.
///
/// Returns a flat iterator over every `ModelEntry` in the database.
pub fn get_all_models() -> impl Iterator<Item = &'static ModelEntry> {
    ALL_PROVIDER_MODELS
        .iter()
        .flat_map(|(_, models)| models.iter())
}

/// Get the total number of models in the database.
pub fn model_count() -> usize {
    ALL_PROVIDER_MODELS.iter().map(|(_, m)| m.len()).sum()
}

/// Get all known provider names.
pub fn get_providers() -> Vec<&'static str> {
    ALL_PROVIDER_MODELS.iter().map(|(name, _)| *name).collect()
}

/// Search models by name or ID pattern (case-insensitive).
pub fn search_models(pattern: &str) -> Vec<&'static ModelEntry> {
    let lower = pattern.to_lowercase();
    get_all_models()
        .filter(|m| m.id.to_lowercase().contains(&lower) || m.name.to_lowercase().contains(&lower))
        .collect()
}

/// Find models that support reasoning/thinking.
pub fn get_reasoning_models() -> Vec<&'static ModelEntry> {
    get_all_models().filter(|m| m.reasoning).collect()
}

/// Find models that support image/vision input.
pub fn get_vision_models() -> Vec<&'static ModelEntry> {
    get_all_models().filter(|m| m.supports_vision()).collect()
}

/// Find the cheapest models by input cost, returning up to `limit` results.
pub fn get_cheapest_models(limit: usize) -> Vec<&'static ModelEntry> {
    let mut all: Vec<_> = get_all_models().collect();
    all.sort_by(|a, b| {
        a.cost_input
            .partial_cmp(&b.cost_input)
            .unwrap_or(std::cmp::Ordering::Equal)
    });
    all.truncate(limit);
    all
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_total_model_count() {
        let count = model_count();
        assert!(count >= 544, "Expected at least 544 models, got {}", count);
    }

    #[test]
    fn test_get_anthropic_model() {
        let m = get_model_entry("anthropic", "claude-sonnet-4-20250514");
        assert!(m.is_some(), "Claude Sonnet 4 should exist");
        let m = m.unwrap();
        assert_eq!(m.provider, "anthropic");
        assert!(m.reasoning);
        assert!(m.supports_vision());
        assert!(m.context_window >= 200_000);
    }

    #[test]
    fn test_get_openai_model() {
        let m = get_model_entry("openai", "gpt-4o");
        assert!(m.is_some(), "GPT-4o should exist");
        let m = m.unwrap();
        assert_eq!(m.provider, "openai");
        assert!(m.supports_vision());
    }

    #[test]
    fn test_provider_models() {
        let anthropic = get_provider_models("anthropic");
        assert!(!anthropic.is_empty(), "Anthropic should have models");
        assert!(anthropic.iter().all(|m| m.provider == "anthropic"));

        let unknown = get_provider_models("nonexistent-provider");
        assert!(unknown.is_empty());
    }

    #[test]
    fn test_search_models() {
        let results = search_models("claude");
        assert!(!results.is_empty(), "Should find Claude models");
        assert!(results
            .iter()
            .all(|m| m.name.to_lowercase().contains("claude")
                || m.id.to_lowercase().contains("claude")));
    }

    #[test]
    fn test_cost_calculation() {
        let m = get_model_entry("openai", "gpt-4o").unwrap();
        // 1M input + 1M output tokens
        let cost = m.calculate_cost(1_000_000, 1_000_000, 0, 0);
        let expected = m.cost_input + m.cost_output;
        assert!(
            (cost - expected).abs() < 0.001,
            "Cost calculation mismatch: got {}, expected {}",
            cost,
            expected
        );
    }

    #[test]
    fn test_reasoning_models() {
        let reasoning = get_reasoning_models();
        assert!(!reasoning.is_empty(), "Should have reasoning models");
        assert!(reasoning.iter().all(|m| m.reasoning));
    }

    #[test]
    fn test_vision_models() {
        let vision = get_vision_models();
        assert!(!vision.is_empty(), "Should have vision models");
        assert!(vision.iter().all(|m| m.supports_vision()));
    }

    #[test]
    fn test_all_providers() {
        let providers = get_providers();
        assert!(providers.contains(&"openai"), "Should have openai");
        assert!(providers.contains(&"anthropic"), "Should have anthropic");
        assert!(providers.contains(&"google"), "Should have google");
        assert!(providers.contains(&"deepseek"), "Should have deepseek");
        assert!(providers.len() >= 28, "Should have at least 28 providers");
    }

    #[test]
    fn test_cheapest_models() {
        let cheapest = get_cheapest_models(5);
        assert_eq!(cheapest.len(), 5);
        // Should be sorted by ascending input cost
        for i in 1..cheapest.len() {
            assert!(cheapest[i].cost_input >= cheapest[i - 1].cost_input);
        }
    }
}