Models API

The Models API lets you browse the OpenModels registry, search for models by name or capability, retrieve full model details, and compare providers serving a given model.

List Models


GET /api/models

Search and list models in the registry with optional filtering and pagination.

Query Parameters

Parameter	Type	Required	Default	Description
`search`	string	No	—	Full-text search across model name and description
`capability`	string	No	—	Filter by capability (e.g. `reasoning`, `vision`, `code-generation`)
`modality`	string	No	—	Filter by modality (e.g. `text`, `image`, `audio`)
`page`	integer	No	`1`	Page number (1-indexed)
`limit`	integer	No	`20`	Items per page (max 100)

Example Request


curl "https://api.openmodels.run/api/models?search=deepseek&capability=reasoning&limit=10"

Example Response


{
  "data": [
    {
      "id": "deepseek-v3",
      "name": "DeepSeek V3",
      "description": "DeepSeek's third-generation large language model featuring mixture-of-experts architecture, strong multilingual capabilities, and competitive performance on reasoning and coding benchmarks.",
      "capabilities": ["chat", "completion", "function-calling", "code-generation", "reasoning"],
      "modalities": ["text", "code"],
      "context_window": 128000,
      "licensing": "other",
      "created_at": "2024-12-01T00:00:00.000Z",
      "updated_at": "2025-01-15T00:00:00.000Z"
    },
    {
      "id": "deepseek-r1",
      "name": "DeepSeek R1",
      "description": "DeepSeek's reasoning-focused model with chain-of-thought capabilities and strong performance on math and logic benchmarks.",
      "capabilities": ["chat", "completion", "reasoning"],
      "modalities": ["text", "code"],
      "context_window": 128000,
      "licensing": "other",
      "created_at": "2025-01-20T00:00:00.000Z",
      "updated_at": "2025-02-01T00:00:00.000Z"
    }
  ],
  "pagination": {
    "page": 1,
    "limit": 10,
    "total": 2
  }
}

Response Fields

Field	Type	Description
`data`	array	Array of model objects
`data[].id`	string	Unique model identifier (kebab-case)
`data[].name`	string	Human-readable display name
`data[].description`	string	Detailed description of the model
`data[].capabilities`	string[]	Supported capabilities (e.g. `chat`, `vision`, `reasoning`)
`data[].modalities`	string[]	Supported input/output modalities (e.g. `text`, `image`, `audio`)
`data[].context_window`	integer	Maximum context window size in tokens
`data[].licensing`	string	License type (`proprietary`, `apache-2.0`, `mit`, `other`, etc.)
`data[].created_at`	string	ISO 8601 timestamp when the model was added
`data[].updated_at`	string	ISO 8601 timestamp when the model was last updated
`pagination.page`	integer	Current page number
`pagination.limit`	integer	Items per page
`pagination.total`	integer	Total number of matching models

Get Model


GET /api/models/:id

Retrieve full details for a single model by its unique identifier.

Path Parameters

Parameter	Type	Required	Description
`id`	string	Yes	The model’s unique identifier (e.g. `gpt-5`, `deepseek-v3`)

Example Request


curl "https://api.openmodels.run/api/models/gpt-5"

Example Response


{
  "id": "gpt-5",
  "name": "GPT-5",
  "description": "OpenAI's fifth-generation flagship model with significant improvements in reasoning, multimodal understanding, and code generation. Features enhanced instruction following and expanded context window.",
  "capabilities": ["chat", "completion", "function-calling", "vision", "audio", "code-generation", "reasoning"],
  "modalities": ["text", "image", "audio", "code"],
  "context_window": 256000,
  "licensing": "proprietary",
  "created_at": "2025-06-01T00:00:00.000Z",
  "updated_at": "2026-05-01T00:00:00.000Z"
}

Response Fields

Field	Type	Description
`id`	string	Unique model identifier (kebab-case)
`name`	string	Human-readable display name
`description`	string	Detailed description of the model
`capabilities`	string[]	Supported capabilities
`modalities`	string[]	Supported input/output modalities
`context_window`	integer	Maximum context window size in tokens
`licensing`	string	License type
`created_at`	string	ISO 8601 timestamp when the model was added
`updated_at`	string	ISO 8601 timestamp when the model was last updated

Error Responses

Status	Type	Description
`404`	`NOT_FOUND`	Model with the given ID does not exist

Get Model Providers


GET /api/models/:id/providers

List all providers that serve a given model, including pricing and availability details for each.

Path Parameters

Parameter	Type	Required	Description
`id`	string	Yes	The model’s unique identifier (e.g. `deepseek-v3`)

Example Request


curl "https://api.openmodels.run/api/models/deepseek-v3/providers"

Example Response


{
  "model_id": "deepseek-v3",
  "providers": [
    {
      "provider_id": "deepseek",
      "provider_name": "DeepSeek",
      "provider_model_name": "deepseek-chat",
      "pricing": {
        "input_per_million": 0.27,
        "output_per_million": 1.10,
        "currency": "USD",
        "cache_read_per_million": 0.07
      },
      "rate_limits": {
        "requests_per_minute": 500,
        "tokens_per_minute": 500000
      },
      "context_window_override": null,
      "available_regions": ["global"]
    },
    {
      "provider_id": "together-ai",
      "provider_name": "Together AI",
      "provider_model_name": "deepseek-ai/DeepSeek-V3",
      "pricing": {
        "input_per_million": 0.50,
        "output_per_million": 0.90,
        "currency": "USD"
      },
      "rate_limits": {
        "requests_per_minute": 600,
        "tokens_per_minute": 1000000
      },
      "context_window_override": null,
      "available_regions": ["us-east-1", "eu-west-1"]
    }
  ]
}

Response Fields

Field	Type	Description
`model_id`	string	The requested model’s identifier
`providers`	array	Array of provider mapping objects
`providers[].provider_id`	string	Unique provider identifier
`providers[].provider_name`	string	Human-readable provider name
`providers[].provider_model_name`	string	The provider’s internal model name (used in their API)
`providers[].pricing.input_per_million`	number	Cost per 1M input tokens (USD)
`providers[].pricing.output_per_million`	number	Cost per 1M output tokens (USD)
`providers[].pricing.currency`	string	ISO 4217 currency code
`providers[].pricing.cache_write_per_million`	number	Cost per 1M tokens written to cache (optional)
`providers[].pricing.cache_read_per_million`	number	Cost per 1M tokens read from cache (optional)
`providers[].rate_limits.requests_per_minute`	integer	Max requests per minute
`providers[].rate_limits.tokens_per_minute`	integer	Max tokens per minute
`providers[].context_window_override`	integer \| null	Provider-specific context window override, or `null` for model default
`providers[].available_regions`	string[]	Regions where this model is available at this provider

Error Responses

Status	Type	Description
`404`	`NOT_FOUND`	Model with the given ID does not exist

Compare Providers


GET /api/models/:id/compare

Compare all providers serving a model side-by-side, with pricing and performance data to help you choose the best option.

Path Parameters

Parameter	Type	Required	Description
`id`	string	Yes	The model’s unique identifier (e.g. `gpt-5`)

Example Request


curl "https://api.openmodels.run/api/models/gpt-5/compare"

Example Response


{
  "model_id": "gpt-5",
  "model_name": "GPT-5",
  "comparison": [
    {
      "provider_id": "openai",
      "provider_name": "OpenAI",
      "provider_model_name": "gpt-5",
      "pricing": {
        "input_per_million": 10.0,
        "output_per_million": 40.0,
        "currency": "USD",
        "cache_write_per_million": 5.0,
        "cache_read_per_million": 2.5
      },
      "rate_limits": {
        "requests_per_minute": 500,
        "tokens_per_minute": 500000
      },
      "context_window_override": null,
      "available_regions": ["us-east-1", "eu-west-1"]
    },
    {
      "provider_id": "openrouter",
      "provider_name": "OpenRouter",
      "provider_model_name": "openai/gpt-5",
      "pricing": {
        "input_per_million": 10.0,
        "output_per_million": 40.0,
        "currency": "USD"
      },
      "rate_limits": {
        "requests_per_minute": 200,
        "tokens_per_minute": 400000
      },
      "context_window_override": null,
      "available_regions": ["global"]
    }
  ]
}

Response Fields

Field	Type	Description
`model_id`	string	The requested model’s identifier
`model_name`	string	Human-readable model name
`comparison`	array	Array of provider comparison objects, sorted by input price (ascending)
`comparison[].provider_id`	string	Unique provider identifier
`comparison[].provider_name`	string	Human-readable provider name
`comparison[].provider_model_name`	string	The provider’s internal model name
`comparison[].pricing.input_per_million`	number	Cost per 1M input tokens
`comparison[].pricing.output_per_million`	number	Cost per 1M output tokens
`comparison[].pricing.currency`	string	ISO 4217 currency code
`comparison[].pricing.cache_write_per_million`	number	Cost per 1M cache write tokens (optional)
`comparison[].pricing.cache_read_per_million`	number	Cost per 1M cache read tokens (optional)
`comparison[].rate_limits.requests_per_minute`	integer	Max requests per minute
`comparison[].rate_limits.tokens_per_minute`	integer	Max tokens per minute
`comparison[].context_window_override`	integer \| null	Provider-specific context window override, or `null` for model default
`comparison[].available_regions`	string[]	Regions where this model is available

Error Responses

Status	Type	Description
`404`	`NOT_FOUND`	Model with the given ID does not exist