POST /v1/messages — Anthropic Claude Messages format

The /v1/messages endpoint accepts requests in Anthropic’s native Claude Messages API format. If you already use the anthropic Python or JavaScript SDK, you can redirect it at OpenOpen8 by changing only the base URL — all request and response fields remain identical. OpenOpen8 authenticates you with the token from your dashboard and routes the request to the configured Claude channel. You can also send Claude-format requests to non-Claude upstream channels; OpenOpen8 translates the format automatically where possible.

Endpoint

POST /v1/messages

Authentication

Claude Messages requests use two headers instead of Authorization:

Header	Required	Description
`x-api-key`	Yes	Your OpenOpen8 token
`anthropic-version`	Yes	Must be `2023-06-01`

You may alternatively use Authorization: Bearer YOUR_TOKEN for the API key if your client does not support x-api-key. OpenOpen8 accepts both forms.

Request parameters

model

string

required

The Claude model to use, for example claude-opus-4-5 or claude-3-7-sonnet-20250219. To enable extended thinking, use the -thinking model name suffix: claude-3-7-sonnet-20250219-thinking.

messages

object[]

required

The conversation history. Messages alternate between user and assistant roles. The first message must have role user.

Show message properties

messages[].role

string

required

The message author role. One of "user" or "assistant".

messages[].content

string | object[]

required

The message content. Pass a plain string for text, or an array of content blocks for multimodal input.Each content block is an object with a type field. Supported types:

"text" — a text block with a text field
"image" — an image block with a source object containing type ("base64" or "url"), media_type, and data or url
"tool_use" — a model-generated tool call with id, name, and input
"tool_result" — the result of a tool call with tool_use_id and content

max_tokens

integer

required

The maximum number of tokens to generate. This field is required by the Claude Messages API. For Claude models, the value must not exceed the model’s output token limit.

system

string | object[]

A system prompt that sets context and instructions for the conversation. Pass a plain string, or an array of content blocks for advanced use cases such as caching system prompts.

stream

boolean

default:"false"

When true, the response is returned as a stream of server-sent events using Anthropic’s streaming format. Events include message_start, content_block_start, content_block_delta, content_block_stop, message_delta, and message_stop.

temperature

number

Sampling temperature between 0 and 1. Higher values produce more varied output.

top_p

number

Nucleus sampling probability mass between 0 and 1. Recommended when temperature is not set.

top_k

integer

Sample from only the top k most likely tokens. Not recommended for most use cases.

stop_sequences

string[]

Custom sequences at which the model will stop generating. The stop sequence itself is not included in the output.

tools

object[]

Tools the model may call. Each tool defines a function the model can invoke.

Show tool properties

tools[].name

string

required

The name of the tool. Must match the pattern ^[a-zA-Z0-9_-]{1,64}$.

tools[].description

string

A description of what the tool does. The model uses this to decide when to call it.

tools[].input_schema

object

required

The tool’s input parameters in JSON Schema format. Must have type: "object" at the top level, with a properties map and optional required array.

tool_choice

object

Controls how the model selects tools.

Show tool_choice properties

tool_choice.type

string

required

One of "auto" (model decides), "any" (must call a tool), or "tool" (must call a specific tool).

tool_choice.name

string

Required when type is "tool". The name of the tool to call.

tool_choice.disable_parallel_tool_use

boolean

default:"false"

When true, the model may only call one tool at a time.

thinking

object

Enable extended thinking for supported models. Use the -thinking model name suffix as an alternative.

Show thinking properties

thinking.type

string

required

Must be "enabled".

thinking.budget_tokens

integer

The maximum number of tokens the model may use for internal reasoning before producing its response.

Response fields

string

A unique identifier for this message in the format msg_....

type

string

Always "message" for complete responses.

role

string

Always "assistant" for generated messages.

content

object[]

An array of content blocks in the response.

Show content block properties

content[].type

string

The block type: "text" for text output, "tool_use" when the model calls a tool, or "thinking" for extended thinking content.

content[].text

string

The text content. Present when type is "text".

content[].id

string

The tool call ID. Present when type is "tool_use".

content[].name

string

The tool name. Present when type is "tool_use".

content[].input

object

The tool call arguments. Present when type is "tool_use".

content[].thinking

string

The model’s reasoning content. Present when type is "thinking" and extended thinking is enabled.

model

string

The model that generated the response.

stop_reason

string

Why the model stopped generating. One of "end_turn" (natural end), "max_tokens" (token limit reached), "stop_sequence" (custom stop sequence matched), or "tool_use" (model called a tool).

usage

object

Token counts for this request.

Show usage properties

usage.input_tokens

integer

Number of tokens in the input messages and system prompt.

usage.output_tokens

integer

Number of tokens in the generated response.

usage.cache_creation_input_tokens

integer

Tokens written to the prompt cache, if prompt caching was used.

usage.cache_read_input_tokens

integer

Tokens read from the prompt cache, if prompt caching was used.

Examples

Non-streaming
Streaming
Tool use

curl https://openopen8.ai/v1/messages \
  -H "x-api-key: YOUR_TOKEN" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "max_tokens": 1024,
    "system": "You are a concise technical assistant.",
    "messages": [
      {"role": "user", "content": "Explain what a mutex is in one paragraph."}
    ]
  }'

Example response:

{
  "id": "msg_01XFDUDYJgAACzvnptvVoYEL",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "A mutex (mutual exclusion lock) is a synchronization primitive that ensures only one thread can access a shared resource at a time..."
    }
  ],
  "model": "claude-opus-4-5",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 28,
    "output_tokens": 87,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0
  }
}

cURL

curl https://openopen8.ai/v1/messages \
  -H "x-api-key: YOUR_TOKEN" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "max_tokens": 512,
    "stream": true,
    "messages": [
      {"role": "user", "content": "Write a haiku about databases."}
    ]
  }'

The server sends events in Anthropic’s streaming format:

event: message_start
data: {"type":"message_start","message":{"id":"msg_01abc","type":"message","role":"assistant","content":[],"model":"claude-opus-4-5","stop_reason":null,"usage":{"input_tokens":14,"output_tokens":0}}}

event: content_block_start
data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Rows"}}

event: message_stop
data: {"type":"message_stop"}

cURL

curl https://openopen8.ai/v1/messages \
  -H "x-api-key: YOUR_TOKEN" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-5",
    "max_tokens": 1024,
    "tools": [
      {
        "name": "get_weather",
        "description": "Get the current weather for a location.",
        "input_schema": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "City name, e.g. San Francisco"
            }
          },
          "required": ["location"]
        }
      }
    ],
    "messages": [
      {"role": "user", "content": "What is the weather in Tokyo?"}
    ]
  }'

Format conversion

You can also route Claude-format requests (/v1/messages) to non-Claude upstream channels. OpenOpen8 performs automatic format conversion, translating the Claude Messages format to the upstream provider’s native format. This lets you use a single client format across providers. Conversion is best-effort; some Claude-specific features (such as extended thinking) may not be available on all upstream channels.

Overview

Chat & Completions

Media & Multimodal

Other Endpoints

POST /v1/messages — Anthropic Claude Messages format

Endpoint

Authentication

Request parameters

Response fields

Examples

Format conversion

Overview

Chat & Completions

Media & Multimodal

Other Endpoints

​Endpoint

​Authentication

​Request parameters

​Response fields

​Examples

​Format conversion

Endpoint

Authentication

Request parameters

Response fields

Examples

Format conversion