Enum ModelId 

pub enum ModelId {
    Gemini38Flash,
    GPT6Astra,
    GPT6Sol,
    GPT61Sol,
    GPT6Luna,
    GPT56Sol,
    GPT56Terra,
    GPT56Luna,
    OpenAIGptOss20b,
    OpenAIGptOss120b,
    ClaudeSonnet5,
    ClaudeSonnet55,
    ClaudeHaiku55,
    ClaudeFable5,
    ClaudeFable51,
    ClaudeOpus5,
    ClaudeOpus55,
    CopilotAuto,
    CopilotGPT52Codex,
    CopilotGPT51CodexMax,
    CopilotGPT54,
    CopilotGPT54Mini,
    DeepSeekFlash,
    MetaMuseSpark11,
    MetaMuseSpark13,
    MetaMuseSpark13Contributor,
    NvidiaNemotron3Ultra550bA55b,
    NvidiaNemotron3Super120bA12b,
    NvidiaNemotron3Nano30bA3b,
    MergeGatewayDefaultRouting,
    MergeGatewayAnthropicClaudeOpus5,
    MergeGatewayAnthropicClaudeOpus55,
    MergeGatewayAnthropicClaudeSonnet5,
    MergeGatewayAnthropicClaudeSonnet55,
    MergeGatewayDeepseekFlash,
    MergeGatewayXaiGrok46,
    MergeGatewayXaiGrok47,
    MergeGatewayMinimaxH3,
    MergeGatewayMoonshotKimiK3,
    MergeGatewayThinkingMachinesInkling,
    MergeGatewayZaiGlm53Flash,
    MergeGatewayZaiGlm53Flashx,
    MergeGatewayOpenAIGpt56Luna,
    MergeGatewayOpenAIGpt56Sol,
    MergeGatewayOpenAIGpt56Terra,
    MergeGatewayGoogleGemini38Flash,
    MergeGatewayAnthropicClaudeHaiku4520251001,
    MergeGatewayAnthropicClaudeHaiku55,
    MergeGatewayAnthropicClaudeFable51,
    MergeGatewayOpenAIGpt6Astra,
    MergeGatewayOpenAIGpt6Sol,
    MergeGatewayOpenAIGpt61Sol,
    MergeGatewayOpenAIGpt6Luna,
    MergeGatewayXiaomimimoMimoV26Pro,
    MergeGatewayXiaomimimoMimoV26Flash,
    MergeGatewayMistralLarge4,
    MistralLarge3,
    MistralLarge4,
    HuggingFaceOpenAIGptOss20b,
    HuggingFaceOpenAIGptOss120b,
    HuggingFaceGlm53FlashTogether,
    HuggingFaceGlm53Together,
    HuggingFaceKimiK3Together,
    HuggingFaceMinimaxM3Novita,
    StepFun37Flash,
    StepFun5Preview,
    EvolinkGemini31Pro,
    EvolinkMinimaxM3,
    EvolinkClaudeHaiku45,
    ZaiGlm53,
    ZaiGlm53Flash,
    ZaiGlm53Flashx,
    MiMoV26Pro,
    MiMoV26Flash,
    MiMoV26ProUltraspeed,
    MoonshotKimiK3,
    OpenCodeGoGlm53,
    OpenCodeGoGpt56Luna,
    OpenCodeGoKimiK3,
    OpenCodeGoMinimaxM3,
    OllamaGptOss20b,
    OllamaGptOss20bCloud,
    OllamaGptOss120bCloud,
    OllamaMinimaxM3Cloud,
    OllamaGlm53Cloud,
    OllamaKimiK3Cloud,
    OllamaGemma4,
    LlamaCppGemma426bA4b,
    LlamaCppGemma4E4b,
    LlamaCppGptOss20b,
    MinimaxM3,
    OpenRouterDeepSeekFlash,
    OpenRouterOpenAIGptOss120b,
    OpenRouterOpenAIGptOss120bFree,
    OpenRouterOpenAIGptOss20b,
    OpenRouterOpenAIGpt6Astra,
    OpenRouterOpenAIGpt6Sol,
    OpenRouterOpenAIGpt6Luna,
    OpenRouterMetaMuseGlimmer30b,
    OpenRouterMetaMuseSpark13,
    OpenRouterGoogleGemini38Flash,
    OpenRouterAnthropicClaudeSonnet5,
    OpenRouterMistralaiMistralLarge2512,
    OpenRouterNexAgiDeepseekV31NexN1,
    OpenRouterZaiGlm53Flash,
    OpenRouterZaiGlm53Flashx,
    OpenRouterMoonshotaiKimiK3,
    OpenRouterXAiGrok46,
    OpenRouterXAiGrok47,
    OpenRouterXiaomiMimoV26Pro,
    OpenRouterXiaomiMimoV26Flash,
    OpenRouterXiaomiMimoV26ProUltraspeed,
    OpenRouterStepfunStep5Preview,
    VercelAnthropicClaudeSonnet5,
    VercelAnthropicClaudeOpus5,
    VercelAnthropicClaudeOpus55,
    VercelAnthropicClaudeHaiku45,
    VercelOpenAiGpt56Sol,
    VercelOpenAiGpt6Astra,
    VercelOpenAiGpt56Luna,
    VercelGoogleGemini38Flash,
    VercelDeepseekFlash,
    VercelMoonshotaiKimiK3,
    VercelMinimaxM3,
    VercelSpacexaiGrok47,
    XaiGrok46,
    XaiGrok47,
    Custom(String, String),
}

Centralized enum for all supported model identifiers

Variants

Gemini38Flash

Gemini 3.6 Flash - Latest flash model with improved capabilities Gemini 3.7 Flash - Flash model with 1M context and tunable thinking levels Gemini 3.8 Flash - Most intelligent Flash for long-horizon SWE, agents, and enterprise workflows (1M context, 64k output, low/medium/high thinking)

GPT6Astra

GPT-6 Astra - Most capable model for hardest end-to-end work with complex reasoning, coding, computer use, and research

GPT6Sol

GPT-6 Sol - Cost-efficient high-end model in the GPT-6 series for demanding professional work

GPT61Sol

GPT-6.1 Sol - Near-Astra performance for complex coding, computer use, and professional work at a lower cost

GPT6Luna

GPT-6 Luna - Fast cost-efficient model in the GPT-6 series for high-volume latency-sensitive workloads

GPT56Sol

GPT-5.6 Sol - Frontier model for complex professional work in the GPT-5.6 family

GPT56Terra

GPT-5.6 Terra - GPT-5.6 model that balances intelligence and cost

GPT56Luna

GPT-5.6 Luna - GPT-5.6 model optimized for cost-sensitive workloads

OpenAIGptOss20b

GPT-OSS 20B - OpenAI’s open-source 20B parameter model using harmony

OpenAIGptOss120b

GPT-OSS 120B - OpenAI’s open-source 120B parameter model using harmony

ClaudeSonnet5

Claude Sonnet 5 - The best combination of speed and intelligence with adaptive thinking on by default

ClaudeSonnet55

Claude Sonnet 5.5 - Latest Sonnet: best speed/intelligence balance, 1M context, 128K output, between_tools as the lowest thinking setting, default effort high

ClaudeHaiku55

Claude Haiku 5.5 - High-volume latency-sensitive work: classification, routing, extraction, subagents; adaptive thinking, 1M context, 128K output, default effort medium

ClaudeFable5

Claude Fable 5 - Anthropic’s most capable widely released model for demanding reasoning and long-horizon agentic work

ClaudeFable51

Claude Fable 5.1 - successor to Fable 5 for demanding reasoning and long-horizon agentic work, 1M context, adaptive thinking always on, cache reads at 1/4 cost

ClaudeOpus5

Claude Opus 5 - Anthropic’s newest Opus-tier model with 1M context, thinking on by default

ClaudeOpus55

Claude Opus 5.5 - Opus-tier successor for long-running agentic coding, adaptive thinking always on, 1M context, 128K output, default effort medium

CopilotAuto

GitHub Copilot auto model selection

CopilotGPT52Codex

GitHub Copilot GPT-5.2 Codex

CopilotGPT51CodexMax

GitHub Copilot GPT-5.1 Codex Max

CopilotGPT54

GitHub Copilot GPT-5.4

CopilotGPT54Mini

GitHub Copilot GPT-5.4 Mini

DeepSeekFlash

DeepSeek V4.1 Flash - Latest flash model with improved reasoning and efficiency

MetaMuseSpark11

Meta Muse Spark 1.1 - Official Meta AI Standard-tier reasoning model

MetaMuseSpark13

Meta Muse Spark 1.3 - Official Meta AI flagship Standard-tier reasoning model, tuned for agentic workflows

MetaMuseSpark13Contributor

Meta Muse Spark 1.3 Contributor tier - opt-in variant with Meta’s discounted data-contribution terms

NvidiaNemotron3Ultra550bA55b

NVIDIA Nemotron 3 Ultra - NVIDIA’s flagship agentic reasoning model via NIM

NvidiaNemotron3Super120bA12b

NVIDIA Nemotron 3 Super - Efficient long-context agentic reasoning model via NIM

NvidiaNemotron3Nano30bA3b

NVIDIA Nemotron 3 Nano - Efficient reasoning and tool-use model via NIM

MergeGatewayDefaultRouting

Merge Gateway’s default route selected by Merge

MergeGatewayAnthropicClaudeOpus5

Anthropic Claude Opus 5 through Merge Gateway

MergeGatewayAnthropicClaudeOpus55

Anthropic Claude Opus 5.5 through Merge Gateway

MergeGatewayAnthropicClaudeSonnet5

Anthropic Claude Sonnet 5 through Merge Gateway

MergeGatewayAnthropicClaudeSonnet55

Anthropic Claude Sonnet 5.5 through Merge Gateway

MergeGatewayDeepseekFlash

Google Gemini 3.6 Flash through Merge Gateway Google Gemini 3.7 Flash through Merge Gateway DeepSeek V4.1 Flash through Merge Gateway

MergeGatewayXaiGrok46

xAI Grok 4.6 through Merge Gateway

MergeGatewayXaiGrok47

xAI Grok 4.7 through Merge Gateway

MergeGatewayMinimaxH3

MiniMax H3 through Merge Gateway

MergeGatewayMoonshotKimiK3

Moonshot Kimi K3 through Merge Gateway

MergeGatewayThinkingMachinesInkling

Thinking Machines Inkling through Merge Gateway

MergeGatewayZaiGlm53Flash

Z.AI GLM-5.3 Flash through Merge Gateway

MergeGatewayZaiGlm53Flashx

Z.AI GLM-5.3 FlashX through Merge Gateway

MergeGatewayOpenAIGpt56Luna

OpenAI GPT-5.6 Luna through Merge Gateway

MergeGatewayOpenAIGpt56Sol

OpenAI GPT-5.6 Sol through Merge Gateway

MergeGatewayOpenAIGpt56Terra

OpenAI GPT-5.6 Terra through Merge Gateway

MergeGatewayGoogleGemini38Flash

Google Gemini 3.8 Flash through Merge Gateway

MergeGatewayAnthropicClaudeHaiku4520251001

Anthropic Claude Haiku 4.5 through Merge Gateway

MergeGatewayAnthropicClaudeHaiku55

Anthropic Claude Haiku 5.5 through Merge Gateway

MergeGatewayAnthropicClaudeFable51

Anthropic Claude Fable 5.1 through Merge Gateway

MergeGatewayOpenAIGpt6Astra

OpenAI GPT-6 Astra through Merge Gateway

MergeGatewayOpenAIGpt6Sol

OpenAI GPT-6 Sol through Merge Gateway

MergeGatewayOpenAIGpt61Sol

OpenAI GPT-6.1 Sol through Merge Gateway

MergeGatewayOpenAIGpt6Luna

OpenAI GPT-6 Luna through Merge Gateway

MergeGatewayXiaomimimoMimoV26Pro

Xiaomi MiMo V2.6 Pro through Merge Gateway

MergeGatewayXiaomimimoMimoV26Flash

Xiaomi MiMo V2.6 Flash through Merge Gateway

MergeGatewayMistralLarge4

Mistral Large 4 through Merge Gateway

MistralLarge3

Mistral Large 3 - State-of-the-art open-weight general-purpose multimodal model

MistralLarge4

Mistral Large 4 - Open-weight MoE flagship (49B active / 1.05T total) with 1M context (Public Preview)

HuggingFaceOpenAIGptOss20b

OpenAI GPT-OSS 20B via Hugging Face router

HuggingFaceOpenAIGptOss120b

OpenAI GPT-OSS 120B via Hugging Face router

HuggingFaceGlm53FlashTogether

Z.AI GLM-5.2 via Novita inference provider on Hugging Face router Z.AI GLM-5.3 Flash via Together inference provider on Hugging Face router

HuggingFaceGlm53Together

Z.AI GLM-5.3 via Together inference provider on Hugging Face router

HuggingFaceKimiK3Together

Kimi K3 via Together on Hugging Face router

HuggingFaceMinimaxM3Novita

MiniMax M3 via Novita on Hugging Face router

StepFun37Flash

Step 3.7 Flash - StepFun’s flagship multimodal reasoning model with tool calling

StepFun5Preview

Step 5 Preview - StepFun’s frontier model for production-scale Agent applications with 1M context

EvolinkGemini31Pro

GPT-5.2 served through the Evolink gateway GPT-5.5 served through the Evolink gateway Gemini 3.1 Pro served through the Evolink gateway (OpenAI SDK format)

EvolinkMinimaxM3

Gemini 3.5 Flash served through the Evolink gateway (OpenAI SDK format) MiniMax-M3 served through the Evolink gateway (OpenAI Chat Completions format)

EvolinkClaudeHaiku45

Claude Haiku 4.5 served through the Evolink gateway (Anthropic Messages API)

ZaiGlm53

GLM-5.3 - Z.ai flagship coding model with frontier long-horizon agentic performance

ZaiGlm53Flash

GLM-5.3 Flash - Z.ai efficient multimodal model with hybrid sparse+linear attention, 320B total / 18B active, 1M context, native vision

ZaiGlm53Flashx

GLM-5.3 FlashX - Z.ai high-speed Flash variant with faster inference (up to 200 tok/s), 320B total / 18B active, 1M context, native vision

MiMoV26Pro

MiMo V2.6 Pro - Xiaomi’s flagship reasoning model with 1M context

MiMoV26Flash

MiMo V2.6 Flash - Xiaomi’s efficient high-volume model with 1M context

MiMoV26ProUltraspeed

MiMo V2.6 Pro UltraSpeed - Xiaomi’s fastest flagship variant with 1M context

MoonshotKimiK3

Kimi K3 - Moonshot.ai’s 2.8T parameter flagship with Delta Attention, native vision, 1M context

OpenCodeGoGlm53

GLM-5.3 - Z.AI flagship for frontier long-horizon coding on OpenCode Go

OpenCodeGoGpt56Luna

GLM-5.2 - Z.AI flagship model included with OpenCode Go GPT-5.6 Luna - OpenAI cost-efficient frontier model on OpenCode Go

OpenCodeGoKimiK3

Kimi K3 - Moonshot flagship 2.8T agentic model on OpenCode Go

OpenCodeGoMinimaxM3

MiniMax M3 - Frontier multimodal coding model on OpenCode Go

OllamaGptOss20b

Muse Spark 1.2 Contributor - Meta long-context reasoning on OpenCode Go (limited regions) GPT-OSS 20B - Open-weight GPT-OSS 20B model served via Ollama locally

OllamaGptOss20bCloud

GPT-OSS 20B Cloud - Cloud-hosted GPT-OSS 20B served via Ollama Cloud

OllamaGptOss120bCloud

GPT-OSS 120B Cloud - Cloud-hosted GPT-OSS 120B served via Ollama Cloud

OllamaMinimaxM3Cloud

MiniMax-M3 Cloud - Cloud-hosted MiniMax-M3 model served via Ollama Cloud

OllamaGlm53Cloud

GLM-5.2 Cloud - Cloud-hosted GLM-5.2 flagship model served via Ollama Cloud GLM-5.3 Cloud - Cloud-hosted GLM-5.3 flagship model served via Ollama Cloud

OllamaKimiK3Cloud

Kimi K3 Cloud - Moonshot Kimi K3 via Ollama Cloud

OllamaGemma4

Gemma 4 - Google Gemma 4 model served via Ollama

LlamaCppGemma426bA4b

Laguna XS.2 - Poolside’s 33B MoE model (3B activated) for agentic coding via Ollama Gemma 4 26B A4B - Desktop Gemma 4 MoE model served through llama.cpp

LlamaCppGemma4E4b

Gemma 4 E4B - Tiny-footprint Gemma 4 model served through llama.cpp

LlamaCppGptOss20b

GPT-OSS 20B - OpenAI open-weight model served through llama.cpp

MinimaxM3

MiniMax-M3 - Frontier multimodal coding model with 1M context

OpenRouterDeepSeekFlash

DeepSeek V4.1 Flash - Latest flash model via OpenRouter

OpenRouterOpenAIGptOss120b

OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter

OpenRouterOpenAIGptOss120bFree

OpenAI gpt-oss-120b:free - Open-weight 120B reasoning model free tier via OpenRouter

OpenRouterOpenAIGptOss20b

OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter

OpenRouterOpenAIGpt6Astra

OpenAI GPT-6 Astra - OpenAI’s flagship model for demanding end-to-end work via OpenRouter

OpenRouterOpenAIGpt6Sol

GPT-6 Sol - Cost-efficient high-end model in the GPT-6 series via OpenRouter

OpenRouterOpenAIGpt6Luna

GPT-6 Luna - Fast cost-efficient model in the GPT-6 series via OpenRouter

OpenRouterMetaMuseGlimmer30b

Meta Muse Glimmer 30B via OpenRouter

OpenRouterMetaMuseSpark13

Meta Muse Spark 1.2 via OpenRouter Meta Muse Spark 1.3 via OpenRouter

OpenRouterGoogleGemini38Flash

Gemini 3.7 Flash - Flash model with 1M context and tunable thinking levels via OpenRouter Gemini 3.8 Flash - Most intelligent Flash for long-horizon SWE/agents with 1M context via OpenRouter

OpenRouterAnthropicClaudeSonnet5

Claude Sonnet 5 - Anthropic Claude Sonnet 5 listing

OpenRouterMistralaiMistralLarge2512

Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter

OpenRouterNexAgiDeepseekV31NexN1

DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter

OpenRouterZaiGlm53Flash

GLM-5.2 - Z.AI GLM-5.2 flagship model for long-horizon tasks via OpenRouter GLM-5.3 Flash - Z.AI efficient multimodal model with hybrid sparse+linear attention via OpenRouter

OpenRouterZaiGlm53Flashx

GLM-5.3 FlashX - Z.AI high-speed Flash variant with faster inference via OpenRouter

OpenRouterMoonshotaiKimiK3

Kimi K3 - Moonshot AI’s 2.8T parameter flagship via OpenRouter

OpenRouterXAiGrok46

Grok 4.6 - xAI’s flagship reasoning model with reasoning_effort support via OpenRouter

OpenRouterXAiGrok47

Grok 4.7 - xAI’s flagship reasoning model with reasoning_effort support via OpenRouter

OpenRouterXiaomiMimoV26Pro

MiMo-V2.6-Pro - Xiaomi’s flagship agentic model for complex software engineering via OpenRouter

OpenRouterXiaomiMimoV26Flash

MiMo-V2.6-Flash - Xiaomi’s efficient high-volume agentic model via OpenRouter

OpenRouterXiaomiMimoV26ProUltraspeed

MiMo-V2.6-Pro-UltraSpeed - Xiaomi’s fastest flagship variant via OpenRouter

OpenRouterStepfunStep5Preview

Step 5 Preview - StepFun’s flagship agentic model via OpenRouter

VercelAnthropicClaudeSonnet5

Claude Sonnet 5 served through the Vercel AI Gateway

VercelAnthropicClaudeOpus5

Claude Opus 5 served through the Vercel AI Gateway

VercelAnthropicClaudeOpus55

Claude Opus 5.5 served through the Vercel AI Gateway

VercelAnthropicClaudeHaiku45

Claude Haiku 4.5 served through the Vercel AI Gateway

VercelOpenAiGpt56Sol

GPT-5.6 Sol served through the Vercel AI Gateway

VercelOpenAiGpt6Astra

GPT-6 Astra served through the Vercel AI Gateway

VercelOpenAiGpt56Luna

GPT-5.6 Luna served through the Vercel AI Gateway

VercelGoogleGemini38Flash

GPT-5.3 Codex served through the Vercel AI Gateway Gemini 3.1 Pro Preview served through the Vercel AI Gateway Gemini 3.8 Flash served through the Vercel AI Gateway

VercelDeepseekFlash

DeepSeek V4.1 Flash served through the Vercel AI Gateway

VercelMoonshotaiKimiK3

Kimi K3 served through the Vercel AI Gateway

VercelMinimaxM3

MiniMax M3 served through the Vercel AI Gateway

VercelSpacexaiGrok47

Grok 4.7 served through the Vercel AI Gateway

XaiGrok46

Grok 4.6 - xAI’s flagship reasoning model with reasoning_effort support (500k context)

XaiGrok47

Grok 4.7 - xAI’s flagship reasoning model with reasoning_effort support (500k context)

Custom(String, String)

User-defined model not in the hardcoded catalog. Carries the provider key string and model identifier string.

Implementations

impl ModelId

pub fn as_str(&self) -> Cow<'static, str>

Convert the model identifier to its string representation used in API calls and configurations.

Returns Cow<'static, str> because custom user-defined models carry runtime strings that may not be 'static.

impl ModelId

pub fn preferred_lightweight_variant(&self) -> Option<Self>

Preferred built-in lightweight sibling or lower-tier fallback for this model.

pub fn non_reasoning_variant(&self) -> Option<Self>

Attempt to find a non-reasoning variant for this model.

pub fn is_flash_variant(&self) -> bool

Check if this is a “flash” variant (optimized for speed)

pub fn is_pro_variant(&self) -> bool

Check if this is a “pro” variant (optimized for capability)

pub fn is_efficient_variant(&self) -> bool

Check if this is an optimized/efficient variant

pub fn is_top_tier(&self) -> bool

Check if this is a top-tier model

pub fn is_reasoning_variant(&self) -> bool

Determine whether the model is a reasoning-capable variant

pub fn supports_tool_calls(&self) -> bool

Determine whether the model supports tool calls/function execution

pub fn input_modalities(&self) -> &'static [&'static str]

Ordered list of supported input modalities when VT Code has metadata for this model.

pub fn generation(&self) -> &'static str

Get the generation/version string for this model

pub fn supports_apply_patch_tool(&self) -> bool

Determine if this model supports optimized apply_patch tool

impl ModelId

pub fn openrouter_vendor(&self) -> Option<&'static str>

Return the OpenRouter vendor slug when this identifier maps to a marketplace listing

pub fn all_models() -> Vec<ModelId>

Get all available models as a vector

pub fn models_for_provider(provider: Provider) -> Vec<ModelId>

Get all models for a specific provider

pub fn all_models_with_overrides( overrides: &BTreeMap<String, ProviderOverrideConfig>, ) -> Vec<ModelId>

Return all models including user-defined overrides from config.

Merges the hardcoded model list with custom models defined in [providers.<name>] config sections. Custom models are appended as ModelId::Custom variants keyed by provider name.

pub fn models_for_provider_with_overrides( provider: Provider, overrides: &BTreeMap<String, ProviderOverrideConfig>, ) -> Vec<ModelId>

Get all models for a specific provider, including user-defined overrides.

pub fn from_config( model: &str, provider: &str, provider_overrides: &BTreeMap<String, ProviderOverrideConfig>, custom_providers: &[CustomProviderConfig], ) -> Result<Self, ModelParseError>

Resolve a model identifier against a configuration, falling back to ModelId::from_str.

Models declared under the active provider in [providers.<name>] overrides or by a [[custom_providers]] profile are not part of the static catalog, so they are represented as ModelId::Custom. Matching is scoped to the active provider to avoid mis-routing a model ID shared across providers, mirroring the catalog and custom-provider branches of the subagent resolution path. Local-provider pass-through (arbitrary Ollama/llama.cpp IDs) is intentionally not handled here.

impl ModelId

pub fn fallback_models() -> Vec<ModelId>

Get recommended fallback models in order of preference

pub fn default_orchestrator() -> Self

Get the default orchestrator model (more capable)

pub fn default_orchestrator_for_provider(provider: Provider) -> Self

Get provider-specific defaults for orchestrator

pub fn default_single_for_provider(provider: Provider) -> Self

Get provider-specific defaults for single agent

impl ModelId

pub fn description(&self) -> Cow<'static, str>

Get a description of the model’s characteristics.

Returns Cow<'static, str> because custom user-defined models carry runtime strings that may not be 'static.

impl ModelId

pub fn display_name(&self) -> Cow<'static, str>

Get the display name for the model (human-readable).

Returns Cow<'static, str> because custom user-defined models carry runtime strings that may not be 'static.

impl ModelId

pub fn provider(&self) -> Provider

Get the provider for this model

pub fn supports_reasoning_effort(&self) -> bool

Whether this model supports configurable reasoning effort levels

pub fn supports_reasoning(&self) -> bool

Whether this model exposes structured reasoning output.

Trait Implementations

impl Clone for ModelId

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ModelId

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ModelId

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelId

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for ModelId

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Eq for ModelId

impl FromStr for ModelId

type Err = ModelParseError

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<Self, Self::Err>

Parses a string s to return a value of this type.

impl Hash for ModelId

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl JsonSchema for ModelId

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for ModelId

fn eq(&self, other: &Self) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl Serialize for ModelId

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelId