Skip to main content
GET
/
v1
/
models
List Models
curl --request GET \
  --url http://localhost:8080/v1/models
{
  "data": [
    {
      "id": "openrouter/openai/gpt-4o",
      "canonical_slug": "openai/gpt-4o",
      "name": "OpenAI: GPT-4o",
      "created": 1715558400,
      "context_length": 128000,
      "max_input_tokens": 123,
      "max_output_tokens": 123,
      "architecture": {
        "tokenizer": "GPT",
        "instruct_type": "<string>",
        "input_modalities": [
          "text",
          "image",
          "file"
        ],
        "output_modalities": [
          "text"
        ],
        "modality": "text+image->text"
      },
      "pricing": {
        "prompt": "0.0000025",
        "completion": "0.00001",
        "request": "0",
        "image": "0.003613",
        "web_search": "0",
        "internal_reasoning": "0",
        "input_cache_read": "0.00000125",
        "input_cache_write": "0"
      },
      "top_provider": {
        "context_length": 123,
        "max_completion_tokens": 123,
        "is_moderated": true
      },
      "per_request_limits": {
        "prompt_tokens": 123,
        "completion_tokens": 123
      },
      "supported_parameters": [
        "<string>"
      ],
      "default_parameters": {},
      "hugging_face_id": "<string>",
      "description": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs",
      "owned_by": "openai",
      "supported_methods": [
        "<string>"
      ]
    }
  ],
  "next_page_token": "eyJwYWdlIjoxfQ==",
  "extra_fields": {
    "provider": "openai",
    "request_type": "list_models",
    "latency": 1234,
    "raw_response": {}
  }
}

Query Parameters

​
provider
enum<string>

The provider to list models from. If not set, returns models from all configured providers in Bifrost.

Available options:
openai,
anthropic,
azure,
bedrock,
cohere,
vertex,
mistral,
ollama,
gemini,
groq,
openrouter,
sgl,
parasail,
cerebras
Example:

"openai"

​
page_size
integer

Number of models to return per page. If not specified, the provider's default page size will be used.

​
page_token
string

Token received from previous request to retrieve the next page of results. Omit this parameter to fetch the first page.

Response

Successful response with list of models

​
data
object[]
required

Array of model information objects

​
next_page_token
string

Token to retrieve the next page of results. Omitted if there are no more pages.

Example:

"eyJwYWdlIjoxfQ=="

​
extra_fields
object