OhMyGPT
Models

Retrieve model

GET
/v1/models/{creator}/{model}

Returns detailed information about a specific model. Model IDs use the {creator}/{model} form, so clients must send both path segments, for example /v1/models/openai/gpt-4o.

Path Parameters

creator*string

Model creator namespace (e.g. openai, anthropic)

model*string

Model slug (e.g. gpt-4o, claude-sonnet-4)

Query Parameters

capability?string

Filter by catalog capability (tool_call, reasoning, vision, streaming, etc.).

modality?string

Filter by input or output modality (text, image, audio, video).

service?string

Filter by service type (llm, embedding, tts, stt, image, rerank).

lifecycle?string

Filter by lifecycle status (active, deprecated, sunset).

q?string

Free-text search across model ID, name, and description.

provider?string

Comma-separated provider filter. providers is accepted as an alias.

providers?string

Comma-separated provider filter alias; merged with provider.

input_modalities?string

Comma-separated input modalities.

output_modalities?string

Comma-separated output modalities.

context?integer

Minimum context length filter; accepted for OpenRouter client compatibility.

Range0 <= value
min_context?integer

Alias of context; conflicting values are rejected.

Range0 <= value
min_price?number

Minimum input price in USD per 1M tokens.

Range0 <= value
max_price?number

Maximum input price in USD per 1M tokens.

Range0 <= value
min_output_price?number

Minimum output price in USD per 1M tokens.

Range0 <= value
max_output_price?number

Maximum output price in USD per 1M tokens.

Range0 <= value
arch?string

Filter by derived model family (GPT, Claude, Gemini, DeepSeek, Mistral, Qwen, Other).

category?string

Filter by conservative derived category. Only programming and technology are currently classifiable; other categories return no matches.

Value in"programming""roleplay""marketing""marketing/seo""technology""science""translation""legal""finance""health""trivia""academia"
model_authors?string

Comma-separated creator slugs from the model ID.

min_age_days?integer

Minimum age in days from lifecycle.effective_since; models without that fact do not match.

Range0 <= value
max_age_days?integer

Maximum age in days from lifecycle.effective_since; models without that fact do not match.

Range0 <= value
sort?string

Supported catalog sorts; unknown values are ignored.

Response Body

Successful response

application/json
  1. response
api?string

Native API type of the model

architecture?
available*boolean

Whether the platform currently offers this model. Unavailable models can still be retrieved by ID.

capability?

General capability score from the Epoch Capabilities Index (Epoch AI, epoch.ai/eci, CC BY 4.0), which places models on one scale across many benchmarks even when they were evaluated on different ones. GPT-5 is anchored at 150. Credit Epoch AI wherever the score is shown. Omitted when the index does not cover the model.

context_length?integer
created*integer
description?string
fidelity?
id*string
knowledge_cutoff?string
lifecycle?
limits?

Public /v1/models limits projection. max_prompt_tokens and max_completion_tokens are directional limits.

managed_routing?boolean

The platform schedules this model across its providers under a routing contract. A provider named in the model string or in provider routing options is not honored; each request is charged at the price of the provider that serves it. Omitted when the caller can choose the provider.

modalities?
name?string
object*"model"
Value in"model"
owned_by*string
preference?

Human-preference rating from LMArena's Text Arena leaderboard (lmarena-ai/leaderboard-dataset, CC BY 4.0): an Elo-scale rating from blind pairwise votes on the overall text category. Credit LMArena wherever the rating is shown. It measures which answers people prefer, on a different scale from capability; do not merge, average or convert between the two. Where the leaderboard lists a model once per reasoning effort, the entry without an effort suffix is used, otherwise the effort with the most votes. Omitted when the leaderboard does not cover the model.

pricing?

Public catalog pricing shown in Credits. price_credits is the selling price; list_price_credits is the provider's list price, omitted when the two are equal.

protocols?array<>

Protocol endpoints this model can be called through. Lists what the catalog supports, not whether a given key, account or provider filter can call it right now.

providers?array<>

Static hosting providers available for this model.

service*string

Product type of the model (llm, embedding, image, video, tts, stt, rerank, ocr, …), the same value the service filter matches.

Example Request
curl -X GET 'https://api.ohmygpt.com/v1/models/string/string'
Example Response
{  "api": "string",  "architecture": {    "input_modalities": [      "string"    ],    "modality": "string",    "output_modalities": [      "string"    ]  },  "available": true,  "capability": {    "as_of": "string",    "ci_high": 0,    "ci_low": 0,    "score": 0  },  "context_length": 0,  "created": 0,  "description": "string",  "fidelity": {    "routes": {      "property1": {        "lossy_fields": [          {            "degradation": "string",            "field": "string",            "impact": "string"          }        ],        "score": 0      },      "property2": {        "lossy_fields": [          {            "degradation": "string",            "field": "string",            "impact": "string"          }        ],        "score": 0      }    }  },  "id": "string",  "knowledge_cutoff": "string",  "lifecycle": {    "deprecated_at": "string",    "status": "string",    "successor": "string",    "sunset_at": "string"  },  "limits": {    "max_completion_tokens": 0,    "max_prompt_tokens": 0,    "stream_idle_timeout": 0  },  "managed_routing": true,  "modalities": {    "input": [      "string"    ],    "output": [      "string"    ]  },  "name": "string",  "object": "model",  "owned_by": "string",  "preference": {    "as_of": "string",    "rating": 0,    "rating_lower": 0,    "rating_upper": 0,    "votes": 0  },  "pricing": {    "flat": [      {        "kind": "string",        "list_price_credits": 0,        "params": {          "property1": "string",          "property2": "string"        },        "price_credits": 0      }    ],    "mode": "string",    "rules": [      {        "condition": {          "exclude_ranges": [            {              "end": "2019-08-24T14:15:22Z",              "start": "2019-08-24T14:15:22Z"            }          ],          "max_input": 0,          "min_input": 0,          "params": {            "property1": "string",            "property2": "string"          },          "service_tier": "string",          "time_windows": [            {              "end": "string",              "start": "string"            }          ],          "usage_kind": "llm",          "valid_from": "2019-08-24T14:15:22Z",          "valid_until": "2019-08-24T14:15:22Z",          "weekdays": [            "monday"          ]        },        "kind": "string",        "list_price_credits": 0,        "price_credits": 0      }    ],    "tiered": [      {        "items": [          {            "kind": "string",            "list_price_credits": 0,            "params": {              "property1": "string",              "property2": "string"            },            "price_credits": 0          }        ],        "up_to": 0      }    ],    "variants": [      {        "items": [          {            "kind": "string",            "list_price_credits": 0,            "params": {              "property1": "string",              "property2": "string"            },            "price_credits": 0          }        ],        "name": "string"      }    ]  },  "protocols": [    {      "id": "string",      "label": "string",      "method": "GET",      "model": "string",      "native": true,      "path": "string",      "transport": "http"    }  ],  "providers": [    {      "context": 0,      "data_policy": {        "moderation": "string",        "retention": "string",        "training": true      },      "display_name": "string",      "location": "string",      "max_completion_tokens": 0,      "max_prompt_tokens": 0,      "pricing": {        "flat": [          {            "kind": "string",            "list_price_credits": 0,            "params": {              "property1": "string",              "property2": "string"            },            "price_credits": 0          }        ],        "mode": "string",        "rules": [          {            "condition": {              "exclude_ranges": [                {                  "end": "2019-08-24T14:15:22Z",                  "start": "2019-08-24T14:15:22Z"                }              ],              "max_input": 0,              "min_input": 0,              "params": {                "property1": "string",                "property2": "string"              },              "service_tier": "string",              "time_windows": [                {                  "end": "string",                  "start": "string"                }              ],              "usage_kind": "llm",              "valid_from": "2019-08-24T14:15:22Z",              "valid_until": "2019-08-24T14:15:22Z",              "weekdays": [                "monday"              ]            },            "kind": "string",            "list_price_credits": 0,            "price_credits": 0          }        ],        "tiered": [          {            "items": [              {                "kind": "string",                "list_price_credits": 0,                "params": {                  "property1": "string",                  "property2": "string"                },                "price_credits": 0              }            ],            "up_to": 0          }        ],        "variants": [          {            "items": [              {                "kind": "string",                "list_price_credits": 0,                "params": {                  "property1": "string",                  "property2": "string"                },                "price_credits": 0              }            ],            "name": "string"          }        ]      },      "provider": "string",      "quantization": "string",      "supports_implicit_caching": true    }  ],  "service": "string"}

Create embedding POST

Generate vector representations of text. Supports multiple embedding providers.

Get recent model availability GET

Answers whether the model works right now and when it had trouble over the last 72 hours, for the model as a whole and for each provider that served it. Counted the same way as `/v1/models/{creator}/{model}/stats`: `overall` counts every request for the model by the result the caller received, whoever chose the provider; each provider counts every upstream attempt it was sent. Only rates and minute counts are published.