Quickstart

The OpenModels API gives you programmatic access to the full model registry — search models, filter by capability, and compare providers with pricing and latency data.

Base URL: https://api.openmodels.run

No authentication is required. All endpoints are public and read-only.

Search Models

Find models by name or keyword using the search endpoint:


curl "https://api.openmodels.run/api/models?search=deepseek"

Response:


{
  "data": [
    {
      "id": "deepseek-v3",
      "name": "DeepSeek V3",
      "vendor": "deepseek",
      "capabilities": ["chat", "reasoning", "code"],
      "context_window": 128000,
      "max_output_tokens": 8192
    },
    {
      "id": "deepseek-r1",
      "name": "DeepSeek R1",
      "vendor": "deepseek",
      "capabilities": ["chat", "reasoning"],
      "context_window": 128000,
      "max_output_tokens": 8192
    }
  ],
  "pagination": {
    "page": 1,
    "limit": 20,
    "total": 2
  }
}

Key Response Fields

Field	Description
`id`	Unique model identifier used in other API calls
`vendor`	The organization that created the model
`capabilities`	What the model can do (chat, reasoning, vision, code, etc.)
`context_window`	Maximum input tokens the model accepts
`max_output_tokens`	Maximum tokens the model can generate

Browse Models by Capability

Filter models by what they can do — reasoning, vision, code generation, and more:


curl "https://api.openmodels.run/api/models?capability=vision&limit=5"

Response:


{
  "data": [
    {
      "id": "gpt-4o",
      "name": "GPT-4o",
      "vendor": "openai",
      "capabilities": ["chat", "vision", "code", "reasoning"],
      "context_window": 128000,
      "max_output_tokens": 16384
    },
    {
      "id": "gemini-2-5-pro",
      "name": "Gemini 2.5 Pro",
      "vendor": "google",
      "capabilities": ["chat", "vision", "reasoning", "code"],
      "context_window": 1048576,
      "max_output_tokens": 65536
    }
  ],
  "pagination": {
    "page": 1,
    "limit": 5,
    "total": 12
  }
}

Available Capabilities

Use any of these values with the capability filter:

chat — General conversation
reasoning — Complex multi-step reasoning
vision — Image understanding
code — Code generation and analysis
function_calling — Tool use and function calls

Get Model Details

Retrieve full details for a specific model:


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

Response:


{
  "id": "deepseek-v3",
  "name": "DeepSeek V3",
  "vendor": "deepseek",
  "description": "DeepSeek's flagship general-purpose model with strong reasoning and coding capabilities.",
  "capabilities": ["chat", "reasoning", "code"],
  "context_window": 128000,
  "max_output_tokens": 8192,
  "release_date": "2025-01-20",
  "providers": ["deepseek", "deepinfra", "together", "fireworks"]
}

Compare Providers

See which providers offer a model and compare their pricing and performance:


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

Response:


{
  "model_id": "deepseek-v3",
  "providers": [
    {
      "provider_id": "deepseek",
      "provider_name": "DeepSeek",
      "model_id_on_provider": "deepseek-chat",
      "pricing": {
        "input_per_million": 0.27,
        "output_per_million": 1.10,
        "currency": "USD"
      }
    },
    {
      "provider_id": "deepinfra",
      "provider_name": "DeepInfra",
      "model_id_on_provider": "deepseek-ai/DeepSeek-V3",
      "pricing": {
        "input_per_million": 0.40,
        "output_per_million": 0.89,
        "currency": "USD"
      }
    },
    {
      "provider_id": "together",
      "provider_name": "Together AI",
      "model_id_on_provider": "deepseek-ai/DeepSeek-V3",
      "pricing": {
        "input_per_million": 0.30,
        "output_per_million": 0.90,
        "currency": "USD"
      }
    }
  ]
}

Provider Response Fields

Field	Description
`provider_id`	Unique provider identifier
`model_id_on_provider`	The model ID to use when calling this provider’s API
`pricing.input_per_million`	Cost per 1M input tokens (USD)
`pricing.output_per_million`	Cost per 1M output tokens (USD)

Pagination

All list endpoints support pagination:


curl "https://api.openmodels.run/api/models?page=2&limit=10"

Parameter	Default	Description
`page`	1	Page number (1-indexed)
`limit`	20	Items per page (max 100)

Next Steps

API Reference — Full documentation for all endpoints, parameters, and response schemas
Concepts — Understand the registry structure (models, providers, mappings)
Architecture — How the platform components work together