Enum LlmProvider 

pub enum LlmProvider {
    Anthropic,
    OpenAI,
    GoogleGemini,
    GoogleVertex,
    AzureOpenAI,
    AWSBedrock,
    Ollama,
    XAI,
    Groq,
    Mistral,
    DeepSeek,
    Cohere,
    Perplexity,
    Cerebras,
    TogetherAI,
    FireworksAI,
    AlibabaQwen,
    OpenRouter,
    CloudflareAI,
    Opencode,
}

Supported LLM providers (OpenAI-compatible where applicable)

Variants

Anthropic

Anthropic Claude models (native API)

OpenAI

OpenAI GPT models

GoogleGemini

Google Gemini via AI Studio (OpenAI-compatible) Base: https://generativelanguage.googleapis.com/v1beta/openai/

GoogleVertex

Google Vertex AI (requires GCP auth) Base: https://aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/endpoints/openapi

AzureOpenAI

Azure OpenAI Service Base: https://{resource}.openai.azure.com/openai/deployments/{deployment}

AWSBedrock

AWS Bedrock (OpenAI-compatible via Converse API) Base: https://bedrock-runtime.{region}.amazonaws.com

Ollama

Ollama (local server; can route to Ollama Cloud models) Base: http://localhost:11434

XAI

xAI Grok models Base: https://api.x.ai/v1

Groq

Groq (ultra-fast inference) Base: https://api.groq.com/openai/v1

Mistral

Mistral AI Base: https://api.mistral.ai/v1/

DeepSeek

DeepSeek (research-focused) Base: https://api.deepseek.com/v1

Cohere

Cohere (enterprise NLP) Base: https://api.cohere.ai/v1

Perplexity

Perplexity (search-augmented) Base: https://api.perplexity.ai

Cerebras

Cerebras (wafer-scale inference) Base: https://api.cerebras.ai/v1

TogetherAI

Together AI (open model hosting) Base: https://api.together.xyz/v1

FireworksAI

Fireworks AI (fast open model inference) Base: https://api.fireworks.ai/inference/v1

AlibabaQwen

Alibaba Qwen / DashScope Base: https://dashscope-intl.aliyuncs.com/compatible-mode/v1

OpenRouter

OpenRouter (300+ models, automatic fallbacks) Base: https://openrouter.ai/api/v1

CloudflareAI

Cloudflare AI Gateway (unified endpoint) Base: https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/

Opencode

Opencode AI Base: https://api.opencode.ai/v1

Implementations

impl LlmProvider

pub fn all() -> &'static [LlmProvider]

Get all available providers

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

Get environment variable name for API key

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

Get default base URL for provider

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

Get default model for provider (updated Dec 2025 - using standardized aliases)

pub fn is_anthropic_format(&self) -> bool

Check if provider uses native Anthropic API format

pub fn is_openai_compatible(&self) -> bool

Check if provider uses OpenAI-compatible format

pub fn requires_special_auth(&self) -> bool

Check if provider requires special authentication

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

Get provider display name

Trait Implementations

impl Clone for LlmProvider

fn clone(&self) -> LlmProvider

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LlmProvider

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

Formats the value using the given formatter.

impl Default for LlmProvider

fn default() -> LlmProvider

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LlmProvider

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for LlmProvider

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

Formats the value using the given formatter.

impl Hash for LlmProvider

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 PartialEq for LlmProvider

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for LlmProvider

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for LlmProvider

impl Eq for LlmProvider

impl StructuralPartialEq for LlmProvider