Models

List available models

GET/v1/models

Lists available models. If provider is not specified, lists all models from all configured providers.

Query Parameters

provider?string

Filter by provider (e.g., openai, anthropic, bedrock)

Value in"openai" | "azure" | "anthropic" | "bedrock" | "cohere" | "vertex" | "vllm" | "mistral" | "ollama" | "groq" | "sgl" | "parasail" | "perplexity" | "replicate" | "cerebras" | "gemini" | "openrouter" | "elevenlabs" | "huggingface" | "nebius" | "xai" | "runway" | "fireworks"
page_size?integer

Maximum number of models to return

Range0 <= value
page_token?string

Token for pagination

Response Body

application/json

application/json

application/json

curl -X GET "http://localhost:8080/v1/models"
{
  "data": [
    {
      "id": "string",
      "canonical_slug": "string",
      "name": "string",
      "deployment": "string",
      "created": 0,
      "context_length": 0,
      "max_input_tokens": 0,
      "max_output_tokens": 0,
      "architecture": {
        "modality": "string",
        "tokenizer": "string",
        "instruct_type": "string",
        "input_modalities": [
          "string"
        ],
        "output_modalities": [
          "string"
        ]
      },
      "pricing": {
        "prompt": "string",
        "completion": "string",
        "request": "string",
        "image": "string",
        "web_search": "string",
        "internal_reasoning": "string",
        "input_cache_read": "string",
        "input_cache_write": "string"
      },
      "top_provider": {
        "is_moderated": true,
        "context_length": 0,
        "max_completion_tokens": 0
      },
      "per_request_limits": {
        "prompt_tokens": 0,
        "completion_tokens": 0
      },
      "supported_parameters": [
        "string"
      ],
      "default_parameters": {
        "temperature": 0,
        "top_p": 0,
        "frequency_penalty": 0
      },
      "hugging_face_id": "string",
      "description": "string",
      "owned_by": "string",
      "supported_methods": [
        "string"
      ]
    }
  ],
  "extra_fields": {
    "request_type": "string",
    "provider": "openai",
    "model_requested": "string",
    "model_deployment": "string",
    "latency": 0,
    "chunk_index": 0,
    "raw_request": {},
    "raw_response": {},
    "cache_debug": {
      "cache_hit": true,
      "cache_id": "string",
      "hit_type": "string",
      "requested_provider": "string",
      "requested_model": "string",
      "provider_used": "string",
      "model_used": "string",
      "input_tokens": 0,
      "threshold": 0,
      "similarity": 0
    }
  },
  "next_page_token": "string"
}
{
  "event_id": "string",
  "type": "string",
  "is_bifrost_error": true,
  "status_code": 0,
  "error": {
    "type": "string",
    "code": "string",
    "message": "string",
    "param": "string",
    "event_id": "string"
  },
  "extra_fields": {
    "provider": "openai",
    "model_requested": "string",
    "request_type": "string"
  }
}
{
  "event_id": "string",
  "type": "string",
  "is_bifrost_error": true,
  "status_code": 0,
  "error": {
    "type": "string",
    "code": "string",
    "message": "string",
    "param": "string",
    "event_id": "string"
  },
  "extra_fields": {
    "provider": "openai",
    "model_requested": "string",
    "request_type": "string"
  }
}