List All Models

curl --request GET \
  --url http://localhost:8080/api/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": {}
  }
}

GET

api

models

List All Models

curl --request GET \
  --url http://localhost:8080/api/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

string

Filter models by provider name

key_ids

string

Comma-separated list of key IDs to filter models by

Response

List of available models

data

object[]

required

Array of model information objects

Show child attributes

data.id

string

required

Unique model identifier

Example:

"openrouter/openai/gpt-4o"

data.canonical_slug

string | null

Canonical slug for the model

Example:

"openai/gpt-4o"

data.name

string

Human-readable model name

Example:

"OpenAI: GPT-4o"

data.created

integer | null

Unix timestamp of model creation

Example:

1715558400

data.context_length

integer | null

Maximum context length in tokens

Example:

128000

data.max_input_tokens

integer | null

Maximum input tokens

data.max_output_tokens

integer | null

Maximum output tokens

data.architecture

object

Object describing the model's technical capabilities

Show child attributes

data.architecture.tokenizer

string

Tokenization method used by the model

Example:

"GPT"

data.architecture.instruct_type

string | null

Instruction format type (null if not applicable)

data.architecture.input_modalities

enum<string>[]

Supported input types for the model

Available options:

file,

image,

text,

audio,

video

Example:

["text", "image", "file"]

data.architecture.output_modalities

enum<string>[]

Supported output types for the model

Available options:

text,

image,

audio,

video

Example:

["text"]

data.architecture.modality

string

Primary model modality

Example:

"text+image->text"

data.pricing

object

Lowest price structure for using this model (all values in USD per token/request/unit)

Show child attributes

data.pricing.prompt

string

Cost per input token in USD

Example:

"0.0000025"

data.pricing.completion

string

Cost per output token in USD

Example:

"0.00001"

data.pricing.request

string

Fixed cost per API request in USD

Example:

"0"

data.pricing.image

string

Cost per image input in USD

Example:

"0.003613"

data.pricing.web_search

string

Cost per web search operation in USD

Example:

"0"

data.pricing.internal_reasoning

string

Cost for internal reasoning tokens in USD

Example:

"0"

data.pricing.input_cache_read

string

Cost per cached input token read in USD

Example:

"0.00000125"

data.pricing.input_cache_write

string

Cost per cached input token write in USD

Example:

"0"

data.top_provider

object

Configuration details for the primary provider

Show child attributes

data.top_provider.context_length

integer

Provider-specific context limit in tokens

data.top_provider.max_completion_tokens

integer

Maximum completion tokens

data.top_provider.is_moderated

boolean

Whether content moderation is applied to the model output

data.per_request_limits

object

Rate limiting information (null if no limits)

Show child attributes

data.per_request_limits.prompt_tokens

integer

Maximum prompt tokens per request

data.per_request_limits.completion_tokens

integer

Maximum completion tokens per request

data.supported_parameters

string[] | null

List of supported parameter names

data.default_parameters

object

data.hugging_face_id

string | null

Hugging Face model identifier

data.description

string | null

Description of the model and its capabilities

Example:

"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs"

data.owned_by

string | null

Organization that owns the model

Example:

"openai"

data.supported_methods

string[] | null

List of supported API methods

next_page_token

string

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

Example:

"eyJwYWdlIjoxfQ=="

extra_fields

object

Show child attributes

extra_fields.provider

enum<string>

AI model provider

Available options:

openai,

anthropic,

azure,

bedrock,

cohere,

vertex,

mistral,

ollama,

gemini,

groq,

openrouter,

sgl,

parasail,

elevenlabs,

perplexity,

cerebras,

nebius

Example:

"openai"

extra_fields.request_type

enum<string>

Request type

Available options:

list_models,

text_completion,

chat_completion,

chat_completion_stream,

responses,

responses_stream,

embedding,

speech,

speech_stream,

transcription,

transcription_stream

extra_fields.latency

number

Request latency in milliseconds

Example:

1234

extra_fields.raw_response

object

Raw provider response

Remove a provider Get All Plugins

⌘I

API Reference

Query Parameters

Response