> ## Documentation Index
> Fetch the complete documentation index at: https://docs.linkmodel.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Anthropic Messages
> Anthropic-compatible Messages endpoint. Any LinkModel chat model can be
called here with the native Anthropic request/response shape — point an
Anthropic SDK at this base URL and set `model` to one of the supported names.
Note the Anthropic contract differs from OpenAI: `system` is a top-level
field (not a message), `max_tokens` is required, and the response body is
a list of content blocks rather than `choices`.
Set `stream: true` to receive Server-Sent Events (`text/event-stream`): a
sequence of typed events (`message_start`, `content_block_delta`, …,
`message_stop`).
### Supported models
| Model | Provider | Details |
| --- | --- | --- |
| `claude-opus-4-7` | Claude | Pricing & specs |
| `deepseek-v4-pro` | DeepSeek | Pricing & specs |
| `kimi-k2.6` | Moonshot | Pricing & specs |
## OpenAPI
````yaml /openapi/chat/_anthropic-messages.yaml post /messages
openapi: 3.0.3
info:
title: Anthropic Messages
version: 1.0.0
description: Anthropic-compatible Messages endpoint for LinkModel chat models.
servers:
- url: https://api.linkmodel.ai/v1
description: Production
security:
- bearerAuth: []
tags:
- name: chat
paths:
/messages:
post:
tags:
- chat
summary: Anthropic Messages
description: >
Anthropic-compatible Messages endpoint. Any LinkModel chat model can be
called here with the native Anthropic request/response shape — point an
Anthropic SDK at this base URL and set `model` to one of the supported
names.
Note the Anthropic contract differs from OpenAI: `system` is a top-level
field (not a message), `max_tokens` is required, and the response body
is
a list of content blocks rather than `choices`.
Set `stream: true` to receive Server-Sent Events (`text/event-stream`):
a
sequence of typed events (`message_start`, `content_block_delta`, …,
`message_stop`).
### Supported models
| Model | Provider | Details |
| --- | --- | --- |
| `claude-opus-4-7` | Claude | Pricing & specs |
| `deepseek-v4-pro` | DeepSeek | Pricing & specs |
| `kimi-k2.6` | Moonshot | Pricing & specs |
operationId: anthropic-messages
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- model
- messages
- max_tokens
properties:
model:
type: string
description: >-
ID of the chat model to use. Must be one of the supported
models listed above.
example: claude-opus-4-7
enum:
- claude-opus-4-7
- deepseek-v4-pro
- kimi-k2.6
messages:
type: array
description: Input messages. Alternating user / assistant turns.
items:
type: object
required:
- role
- content
properties:
role:
type: string
enum:
- user
- assistant
example: user
content:
type: string
description: >-
The message content. May also be an array of content
blocks.
example: Hello, who are you?
max_tokens:
type: integer
description: >-
The maximum number of tokens to generate before stopping.
Required.
example: 1024
system:
type: string
description: >-
A system prompt providing context and instructions, set at
the top level.
example: You are a helpful assistant.
stream:
type: boolean
description: If true, the response is streamed as Server-Sent Events.
default: false
stop_sequences:
type: array
description: >
Custom text sequences that will cause the model to stop
generating. The
generated text will not contain the stop sequence.
items:
type: string
responses:
'200':
description: >-
Message result. When `stream` is true, the body is an SSE stream
instead.
content:
application/json:
schema:
type: object
properties:
id:
type: string
example: msg_abc123
type:
type: string
example: message
role:
type: string
example: assistant
model:
type: string
example: claude-opus-4-7
content:
type: array
items:
type: object
properties:
type:
type: string
example: text
text:
type: string
example: I'm Claude, an AI assistant made by Anthropic.
stop_reason:
type: string
enum:
- end_turn
- max_tokens
- stop_sequence
example: end_turn
stop_sequence:
type: string
nullable: true
usage:
type: object
properties:
input_tokens:
type: integer
example: 12
output_tokens:
type: integer
example: 18
text/event-stream:
schema:
type: string
description: >
SSE stream of typed events. Begins with `message_start`,
followed by `content_block_start` / `content_block_delta` /
`content_block_stop`, then `message_delta` and `message_stop`.
'400':
description: Bad request — invalid or missing parameter.
content:
application/json:
schema:
type: object
properties:
code:
type: integer
example: 400
msg:
type: string
example: max_tokens is required
request_id:
type: string
format: uuid
example: 96be7a7d-3e81-4916-a6b8-19b32773a693
'401':
description: Unauthorized — missing or invalid API key.
content:
application/json:
schema:
type: object
properties:
code:
type: integer
example: 401
msg:
type: string
example: invalid api key
request_id:
type: string
format: uuid
example: bff4c295-c7da-4507-9708-4627cb6373ba
'500':
description: >-
Internal error — message creation failed (e.g. insufficient balance
or upstream error).
content:
application/json:
schema:
type: object
properties:
code:
type: integer
example: 500
msg:
type: string
example: 'message failed: billing: code=100601: insufficient balance'
request_id:
type: string
format: uuid
example: 3409f6fb-fa9a-4534-b530-195b5f6f4e32
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
````