The Models API from LLM Gateway — 1 operation(s) for models.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/llmgateway-io:llmgateway-io-models-api"curl "https://apis.io/api/v1/apis?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
version: 1.0.0
title: LLM Gateway Models API
description: 'OpenAI-compatible LLM gateway: chat completions, embeddings, images, audio, video, moderation, OCR, rerank, web search and typed decisions across providers with one API key.'
servers:
- url: https://api.llmgateway.io
- url: http://localhost:4001
tags:
- name: Models
paths:
/v1/models:
get:
operationId: v1_models
summary: Models
description: List the public model catalogue without authentication. With an API key, return only models and provider mappings allowed by its organization compliance policy, IAM rules, and project access, including accessible custom models. Set include_restricted=true to return the public catalogue regardless of these restrictions.
security:
- {}
- bearerAuth: []
parameters:
- schema:
type: string
description: Return the public catalogue instead of the authenticated caller's accessible models. Other query filters still apply. Does not grant permission to call restricted models or include private custom models.
example: 'false'
required: false
description: Return the public catalogue instead of the authenticated caller's accessible models. Other query filters still apply. Does not grant permission to call restricted models or include private custom models.
name: include_restricted
in: query
- schema:
type: string
description: Include deactivated models in the response
example: 'false'
required: false
description: Include deactivated models in the response
name: include_deactivated
in: query
- schema:
type: string
description: Exclude deprecated models from the response
example: 'false'
required: false
description: Exclude deprecated models from the response
name: exclude_deprecated
in: query
- schema:
type: string
description: Only return models and provider mappings whose provider does not train on API data
example: 'false'
required: false
description: Only return models and provider mappings whose provider does not train on API data
name: no_training
in: query
- schema:
type: string
description: Return one entry per provider mapping with `provider/model-id` ids (the gateway's provider-pinned request format) instead of one aggregated entry per model. Each entry carries that specific mapping's pricing, context length, and capabilities.
example: 'false'
required: false
description: Return one entry per provider mapping with `provider/model-id` ids (the gateway's provider-pinned request format) instead of one aggregated entry per model. Each entry carries that specific mapping's pricing, context length, and capabilities.
name: mapped
in: query
responses:
'200':
description: List of available models
headers:
RateLimit-Policy:
schema:
type: string
description: Quota policy as an HTTP Structured Fields list, e.g. "requests";q=60;w=60.
RateLimit:
schema:
type: string
description: Available quota and reset delay, e.g. "requests";r=59;t=60.
RateLimit-Limit:
schema:
type: string
description: Request limit for the current window.
RateLimit-Remaining:
schema:
type: string
description: Requests remaining in the current window.
RateLimit-Reset:
schema:
type: string
description: Seconds until the current window resets.
content:
application/json:
schema:
type: object
properties:
data:
type: array
items:
type: object
properties:
id:
type: string
name:
type: string
display_name:
type: string
description: Human-readable model label, mirroring `name`. Anthropic-format clients such as Claude Code read this field when populating their model picker from gateway model discovery.
aliases:
type: array
items:
type: string
created:
type: number
description:
type: string
family:
type: string
architecture:
type: object
properties:
input_modalities:
type: array
items:
type: string
enum:
- text
- image
- video
- embedding
- audio
output_modalities:
type: array
items:
type: string
enum:
- text
- image
- video
- embedding
- audio
- ocr
- transcription
- rerank
- decision
- search
tokenizer:
type: string
required:
- input_modalities
- output_modalities
top_provider:
type: object
properties:
is_moderated:
type: boolean
required:
- is_moderated
providers:
type: array
items:
type: object
properties:
providerId:
type: string
externalId:
type: string
supportedVideoSizes:
type: array
items:
type: string
supportsVideoAudio:
type: boolean
supportsVideoWithoutAudio:
type: boolean
pricing:
type: object
properties:
prompt:
type: string
completion:
type: string
image:
type: string
input_audio:
type: string
input_audio_cache_read:
type: string
output_audio:
type: string
per_second:
type: object
additionalProperties:
type: string
per_image:
type: object
additionalProperties:
type: string
request:
type: string
input_cache_read:
type: string
input_cache_write:
type: string
input_cache_write_1h:
type: string
ocr_page:
type: string
input_audio_hour:
type: string
required:
- prompt
- completion
streaming:
anyOf:
- type: boolean
- type: string
enum:
- only
vision:
type: boolean
realtime:
type: boolean
description: Whether this mapping is served via the /v1/realtime WebSocket endpoint instead of /v1/chat/completions.
cancellation:
type: boolean
tools:
type: boolean
parallelToolCalls:
type: boolean
reasoning:
type: boolean
reasoning_efforts:
type: array
items:
type: string
enum:
- none
- minimal
- low
- medium
- high
- xhigh
- max
description: Exact reasoning_effort values this provider mapping accepts, in ascending order of effort. Omitted when the supported values are not declared for the mapping.
reasoning_modes:
type: array
items:
type: string
enum:
- standard
- pro
description: Exact reasoning.mode values this provider mapping accepts. Omitted when the mapping accepts no explicit mode.
min_cacheable_tokens:
type: number
description: Minimum prompt length (in tokens) the provider requires before a prompt-cache write can occur. cache_control markers on shorter prompts are accepted but silently not cached by the provider.
max_output:
type: number
description: Maximum output tokens this provider mapping accepts as max_tokens; larger requests are rejected with HTTP 400. Omitted when the mapping declares no limit (any max_tokens is accepted).
stability:
type: string
enum:
- stable
- beta
- unstable
- experimental
required:
- providerId
- externalId
- streaming
- vision
- cancellation
- tools
- parallelToolCalls
- reasoning
pricing:
type: object
properties:
prompt:
type: string
completion:
type: string
image:
type: string
input_audio:
type: string
input_audio_cache_read:
type: string
output_audio:
type: string
per_second:
type: object
additionalProperties:
type: string
per_image:
type: object
additionalProperties:
type: string
request:
type: string
input_cache_read:
type: string
input_cache_write:
type: string
input_cache_write_1h:
type: string
web_search:
type: string
internal_reasoning:
type: string
ocr_page:
type: string
input_audio_hour:
type: string
required:
- prompt
- completion
context_length:
type: number
max_output:
type: number
description: Largest max_tokens value guaranteed to be accepted regardless of which provider mapping serves the request (the minimum across still-servable mappings that declare a limit; deactivated mappings are excluded). Omitted when no such mapping declares one.
per_request_limits:
type: object
additionalProperties:
type: string
supported_parameters:
type: array
items:
type: string
json_output:
type: boolean
structured_outputs:
type: boolean
free:
type: boolean
deprecated_at:
type: string
deactivated_at:
type: string
stability:
type: string
enum:
- stable
- beta
- unstable
- experimental
required:
- id
- name
- display_name
- family
- architecture
- top_provider
- providers
- pricing
- json_output
- structured_outputs
required:
- data
'400':
description: Invalid request body or parameters.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'401':
description: Missing or invalid API key.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'402':
description: Insufficient credits or plan limits reached.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'403':
description: Forbidden request or upstream response.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'404':
description: Unknown model or upstream not-found response.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'408':
description: Request timeout.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'410':
description: Archived or unavailable project.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'413':
description: Request too large.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'415':
description: Unsupported media type.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'429':
description: Rate limited. Response headers describe only LLMGateway-enforced limits; upstream provider headers are not forwarded. Honor Retry-After when present.
headers:
RateLimit-Policy:
schema:
type: string
description: Quota policy as an HTTP Structured Fields list, e.g. "requests";q=60;w=60.
RateLimit:
schema:
type: string
description: Available quota and reset delay, e.g. "requests";r=59;t=60.
RateLimit-Limit:
schema:
type: string
description: Request limit for the current window.
RateLimit-Remaining:
schema:
type: string
description: Requests remaining in the current window.
RateLimit-Reset:
schema:
type: string
description: Seconds until the current window resets.
Retry-After:
schema:
type: string
description: Seconds to wait before retrying.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'500':
description: Internal server error.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'502':
description: Failed to connect to the upstream provider.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'503':
description: Service unavailable upstream response.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'504':
description: Upstream provider timeout.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
'529':
description: Gateway overloaded.
headers:
Retry-After:
schema:
type: string
description: Seconds to wait before retrying.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIError'
tags:
- Models
components:
schemas:
OpenAIError:
type: object
properties:
error:
type: object
properties:
message:
type: string
type:
type: string
param:
type:
- string
- 'null'
code:
type:
- string
- 'null'
required:
- message
- type
- param
- code
required:
- error
description: OpenAI-compatible error object.
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Bearer token authentication using API keys
externalDocs:
url: https://docs.llmgateway.io
description: LLMGateway Documentation