The Messages API from LLM Gateway — 1 operation(s) for messages.
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-messages-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 Messages 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: Messages
paths:
/v1/messages:
post:
operationId: v1_messages
summary: Anthropic Messages
description: Create a message using Anthropic's API format
security:
- bearerAuth: []
requestBody:
content:
application/json:
schema:
type: object
properties:
model:
type: string
description: The model to use for completion
example: claude-3-5-sonnet-20241022
messages:
type: array
items:
type: object
properties:
role:
type: string
enum:
- system
- developer
- user
- assistant
- tool
- function
content:
anyOf:
- type: string
- type: array
items:
anyOf:
- type: object
properties:
type:
type: string
enum:
- text
text:
type: string
cache_control:
type: object
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
required:
- type
- text
- type: object
properties:
type:
type: string
enum:
- image
source:
type: object
properties:
type:
type: string
enum:
- base64
media_type:
type: string
data:
type: string
required:
- type
- media_type
- data
required:
- type
- source
- type: object
properties:
type:
type: string
enum:
- tool_use
id:
type: string
name:
type: string
input:
type: object
additionalProperties: {}
required:
- type
- id
- name
- input
- type: object
properties:
type:
type: string
enum:
- tool_result
tool_use_id:
type: string
content:
anyOf:
- type: string
- type: array
items: {}
is_error:
type: boolean
cache_control:
type: object
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
required:
- type
- tool_use_id
- type: object
properties:
type:
type: string
enum:
- thinking
thinking:
type: string
signature:
type: string
required:
- type
- thinking
- type: object
properties:
type:
type: string
enum:
- redacted_thinking
data:
type: string
required:
- type
- data
- type: object
properties:
type:
type: string
enum:
- server_tool_use
id:
type: string
name:
type: string
input:
type: object
additionalProperties: {}
required:
- type
- id
- name
- type: object
properties:
type:
type: string
enum:
- web_search_tool_result
tool_use_id:
type: string
content:
anyOf:
- type: array
items: {}
- type: object
additionalProperties: {}
required:
- type
- tool_use_id
- type: object
properties:
type:
type: string
enum:
- tool_search_tool_result
tool_use_id:
type: string
content:
type: object
additionalProperties: {}
required:
- type
- tool_use_id
- type: object
properties:
type:
type: string
enum:
- tool_addition
- tool_removal
tool:
anyOf:
- type: object
properties:
type:
type: string
enum:
- tool_reference
name:
type: string
required:
- type
- name
- type: object
properties:
type:
type: string
enum:
- tool_definition
definition:
type: object
properties:
type:
type: string
enum:
- custom
name:
type: string
description:
type: string
input_schema:
type: object
additionalProperties: {}
cache_control:
type:
- object
- 'null'
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
defer_loading:
type: boolean
required:
- name
- input_schema
required:
- type
- definition
cache_control:
type: object
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
required:
- type
- tool
- type: object
properties:
type:
type: string
required:
- type
tool_call_id:
type: string
name:
type: string
tool_calls:
type: array
items:
type: object
properties:
id:
type: string
type:
type: string
enum:
- function
function:
type: object
properties:
name:
type: string
arguments:
type: string
required:
- name
- arguments
required:
- id
- type
- function
function_call:
type: object
properties:
id:
type: string
name:
type: string
arguments:
anyOf:
- type: string
- type: object
additionalProperties: {}
required:
- name
- arguments
required:
- role
- content
description: Array of message objects
max_tokens:
type: number
minimum: 1
description: Maximum number of tokens to generate
example: 1024
system:
anyOf:
- type: string
- type: array
items:
type: object
properties:
type:
type: string
enum:
- text
text:
type: string
cache_control:
type: object
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
required:
- type
- text
description: System prompt to provide context
temperature:
type: number
minimum: 0
maximum: 1
description: Sampling temperature between 0 and 1
example: 0.7
tools:
type: array
items:
anyOf:
- type: object
properties:
type:
type: string
enum:
- custom
name:
type: string
description:
type: string
input_schema:
type: object
additionalProperties: {}
cache_control:
type:
- object
- 'null'
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
defer_loading:
type: boolean
required:
- name
- input_schema
- type: object
properties:
type:
type: string
pattern: ^tool_search_tool
name:
type: string
required:
- type
- type: object
properties:
type:
type: string
name:
type: string
max_uses:
type: number
allowed_domains:
type: array
items:
type: string
blocked_domains:
type: array
items:
type: string
user_location:
type: object
properties:
type:
type: string
enum:
- approximate
city:
type: string
region:
type: string
country:
type: string
timezone:
type: string
cache_control:
type:
- object
- 'null'
properties:
type:
type: string
enum:
- ephemeral
ttl:
type: string
enum:
- 5m
- 1h
required:
- type
required:
- type
- name
description: Available tools for the model to use
stream:
type: boolean
default: false
description: Whether to stream the response
example: false
metadata:
type: object
properties:
user_id:
type: string
description: Anthropic request metadata. Claude Code embeds the session id in user_id, which the gateway uses for sticky routing.
thinking:
type: object
properties:
type:
type: string
budget_tokens:
type: integer
exclusiveMinimum: 0
required:
- type
description: Anthropic extended-thinking configuration. Mapped onto the gateway's unified reasoning controls so the requested effort reaches the provider.
output_config:
type: object
properties:
effort:
type: string
enum:
- none
- minimal
- low
- medium
- high
- xhigh
- max
description: Anthropic output configuration. `effort` controls adaptive reasoning depth on Opus 4.7+ models.
safeguards:
type: array
items:
type: object
properties:
type:
type: string
required:
- type
description: Anthropic server-side safeguard review, sent by Claude Code in auto mode with its paired `anthropic-beta` value. Forwarded to the Anthropic API only; the verdicts come back as `safeguard_results`.
required:
- model
- messages
- max_tokens
responses:
'200':
description: Successful response
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:
id:
type: string
type:
type: string
enum:
- message
role:
type: string
enum:
- assistant
model:
type: string
content:
type: array
items:
type: object
properties:
type:
type: string
enum:
- text
- tool_use
- thinking
- server_tool_use
- web_search_tool_result
- tool_search_tool_result
text:
type: string
thinking:
type: string
id:
type: string
name:
type: string
input:
type: object
additionalProperties: {}
tool_use_id:
type: string
content:
anyOf:
- type: array
items: {}
- type: object
additionalProperties: {}
required:
- type
stop_reason:
type:
- string
- 'null'
enum:
- end_turn
- max_tokens
- stop_sequence
- tool_use
- pause_turn
- refusal
stop_sequence:
type:
- string
- 'null'
usage:
type: object
properties:
input_tokens:
type: number
output_tokens:
type: number
cache_creation_input_tokens:
type: number
default: 0
cache_read_input_tokens:
type: number
default: 0
cache_creation:
type: object
properties:
ephemeral_5m_input_tokens:
type: number
ephemeral_1h_input_tokens:
type: number
required:
- ephemeral_5m_input_tokens
- ephemeral_1h_input_tokens
required:
- input_tokens
- output_tokens
metadata:
type: object
additionalProperties: {}
description: 'Gateway routing metadata, the same object /v1/chat/completions returns: used_provider, used_model, used_region and routing attempts. On streams it rides on the message_delta event.'
safeguard_results:
type: array
items:
type: object
additionalProperties: {}
description: Anthropic's server-side safeguard verdicts, returned verbatim when the request carried `safeguards`. On streams it rides on the message_delta event's delta.
required:
- id
- type
- role
- model
- content
- stop_reason
- stop_sequence
- usage
text/event-stream:
schema:
type: string
'400':
description: Invalid request body or parameters.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'401':
description: Missing or invalid API key.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'402':
description: Insufficient credits or plan limits reached.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'403':
description: Forbidden request or upstream response.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'404':
description: Unknown model or upstream not-found response.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'408':
description: Request timeout.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'410':
description: Archived or unavailable project.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'413':
description: Request too large.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'415':
description: Unsupported media type.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'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/AnthropicError'
'500':
description: Internal server error.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'502':
description: Failed to connect to the upstream provider.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'503':
description: Service unavailable upstream response.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'504':
description: Upstream provider timeout.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
'529':
description: Gateway overloaded.
headers:
Retry-After:
schema:
type: string
description: Seconds to wait before retrying.
content:
application/json:
schema:
$ref: '#/components/schemas/AnthropicError'
tags:
- Messages
components:
schemas:
AnthropicError:
type: object
properties:
type:
type: string
enum:
- error
error:
type: object
properties:
type:
type: string
message:
type: string
required:
- type
- message
required:
- type
- error
description: Anthropic-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