List Llm Models

client.models.list(?, ?): ModelListResponse { context_window, max_context_window, model, 21 more }

get/v1/models/

List available LLM models using the asynchronous implementation for improved performance.

Returns Model format which extends LLMConfig with additional metadata fields. Legacy LLMConfig fields are marked as deprecated but still available for backward compatibility.

ParametersExpand Collapse

query: ModelListParams { provider_category, provider_name, provider_type }

provider_category?: Array<ProviderCategory> | null

Accepts one of the following:

"base"

"byok"

provider_name?: string | null

provider_type?: ProviderType | null

Accepts one of the following:

"anthropic"

"azure"

"bedrock"

"cerebras"

"deepseek"

"google_ai"

"google_vertex"

"groq"

"hugging-face"

"letta"

"lmstudio_openai"

"mistral"

"ollama"

"openai"

"together"

"vllm"

"xai"

ReturnsExpand Collapse

ModelListResponse = Array<Model { context_window, max_context_window, model, 21 more } >

Deprecatedcontext_window: number

Deprecated: Use 'max_context_window' field instead. The context window size for the model.

max_context_window: number

The maximum context window for the model

Deprecatedmodel: string

Deprecated: Use 'name' field instead. LLM model name.

Deprecatedmodel_endpoint_type: "openai" | "anthropic" | "google_ai" | 18 more

Deprecated: Use 'provider_type' field instead. The endpoint type for the model.

Accepts one of the following:

"openai"

"anthropic"

"google_ai"

"google_vertex"

"azure"

"groq"

"ollama"

"webui"

"webui-legacy"

"lmstudio"

"lmstudio-legacy"

"lmstudio-chatcompletions"

"llamacpp"

"koboldcpp"

"vllm"

"hugging-face"

"mistral"

"together"

"bedrock"

"deepseek"

"xai"

name: string

The actual model name used by the provider

provider_type: ProviderType

The type of the provider

Accepts one of the following:

"anthropic"

"azure"

"bedrock"

"cerebras"

"deepseek"

"google_ai"

"google_vertex"

"groq"

"hugging-face"

"letta"

"lmstudio_openai"

"mistral"

"ollama"

"openai"

"together"

"vllm"

"xai"

Deprecatedcompatibility_type?: "gguf" | "mlx" | null

Deprecated: The framework compatibility type for the model.

Accepts one of the following:

"gguf"

"mlx"

display_name?: string | null

A human-friendly display name for the model.

Deprecatedenable_reasoner?: boolean

Deprecated: Whether or not the model should use extended thinking if it is a 'reasoning' style model.

Deprecatedfrequency_penalty?: number | null

Deprecated: Positive values penalize new tokens based on their existing frequency in the text so far.

handle?: string | null

The handle for this config, in the format provider/model-name.

Deprecatedmax_reasoning_tokens?: number

Deprecated: Configurable thinking budget for extended thinking.

Deprecatedmax_tokens?: number | null

Deprecated: The maximum number of tokens to generate.

Deprecatedmodel_endpoint?: string | null

Deprecated: The endpoint for the model.

model_type?: "llm"

Type of model (llm or embedding)

Accepts one of the following:

"llm"

Deprecatedmodel_wrapper?: string | null

Deprecated: The wrapper for the model.

Deprecatedparallel_tool_calls?: boolean | null

Deprecated: If set to True, enables parallel tool calling.

Deprecatedprovider_category?: ProviderCategory | null

Deprecated: The provider category for the model.

Accepts one of the following:

"base"

"byok"

provider_name?: string | null

The provider name for the model.

Deprecatedput_inner_thoughts_in_kwargs?: boolean | null

Deprecated: Puts 'inner_thoughts' as a kwarg in the function call.

Deprecatedreasoning_effort?: "minimal" | "low" | "medium" | "high" | null

Deprecated: The reasoning effort to use when generating text reasoning models.

Accepts one of the following:

"minimal"

"low"

"medium"

"high"

Deprecatedtemperature?: number

Deprecated: The temperature to use when generating text with the model.

Deprecatedtier?: string | null

Deprecated: The cost tier for the model (cloud only).

Deprecatedverbosity?: "low" | "medium" | "high" | null

Deprecated: Soft control for how verbose model output should be.

Accepts one of the following:

"low"

"medium"

"high"

List Llm Models

import Letta from '@letta-ai/letta-client';

const client = new Letta({
  apiKey: 'My API Key',
});

const models = await client.models.list();

console.log(models);

[
  {
    "context_window": 0,
    "max_context_window": 0,
    "model": "model",
    "model_endpoint_type": "openai",
    "name": "name",
    "provider_type": "anthropic",
    "compatibility_type": "gguf",
    "display_name": "display_name",
    "enable_reasoner": true,
    "frequency_penalty": 0,
    "handle": "handle",
    "max_reasoning_tokens": 0,
    "max_tokens": 0,
    "model_endpoint": "model_endpoint",
    "model_type": "llm",
    "model_wrapper": "model_wrapper",
    "parallel_tool_calls": true,
    "provider_category": "base",
    "provider_name": "provider_name",
    "put_inner_thoughts_in_kwargs": true,
    "reasoning_effort": "minimal",
    "temperature": 0,
    "tier": "tier",
    "verbosity": "low"
  }
]

Returns Examples

[
  {
    "context_window": 0,
    "max_context_window": 0,
    "model": "model",
    "model_endpoint_type": "openai",
    "name": "name",
    "provider_type": "anthropic",
    "compatibility_type": "gguf",
    "display_name": "display_name",
    "enable_reasoner": true,
    "frequency_penalty": 0,
    "handle": "handle",
    "max_reasoning_tokens": 0,
    "max_tokens": 0,
    "model_endpoint": "model_endpoint",
    "model_type": "llm",
    "model_wrapper": "model_wrapper",
    "parallel_tool_calls": true,
    "provider_category": "base",
    "provider_name": "provider_name",
    "put_inner_thoughts_in_kwargs": true,
    "reasoning_effort": "minimal",
    "temperature": 0,
    "tier": "tier",
    "verbosity": "low"
  }
]