Create an Anthropic Messages-compatible response

POST

messages

curl --request POST \
  --url https://api.example.com/v1/messages \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "max_tokens": 499995,
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "system": "<string>",
  "stream": false,
  "temperature": 0.5,
  "top_p": 0.5,
  "top_k": 1,
  "stop_sequences": [
    "<string>"
  ],
  "tools": [
    {}
  ],
  "tool_choice": {
    "name": "<string>",
    "disable_parallel_tool_use": true
  },
  "thinking": {
    "budget_tokens": 499995
  },
  "output_config": {
    "format": {
      "type": "<string>",
      "schema": {}
    }
  },
  "context_management": {
    "edits": [
      {
        "type": "<string>",
        "keep": "<string>"
      }
    ]
  },
  "metadata": {},
  "flagged_categories": []
}
'

import requests

url = "https://api.example.com/v1/messages"

payload = {
    "model": "<string>",
    "max_tokens": 499995,
    "messages": [{ "content": "<string>" }],
    "system": "<string>",
    "stream": False,
    "temperature": 0.5,
    "top_p": 0.5,
    "top_k": 1,
    "stop_sequences": ["<string>"],
    "tools": [{}],
    "tool_choice": {
        "name": "<string>",
        "disable_parallel_tool_use": True
    },
    "thinking": { "budget_tokens": 499995 },
    "output_config": { "format": {
            "type": "<string>",
            "schema": {}
        } },
    "context_management": { "edits": [
            {
                "type": "<string>",
                "keep": "<string>"
            }
        ] },
    "metadata": {},
    "flagged_categories": []
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    max_tokens: 499995,
    messages: [{content: '<string>'}],
    system: '<string>',
    stream: false,
    temperature: 0.5,
    top_p: 0.5,
    top_k: 1,
    stop_sequences: ['<string>'],
    tools: [{}],
    tool_choice: {name: '<string>', disable_parallel_tool_use: true},
    thinking: {budget_tokens: 499995},
    output_config: {format: {type: '<string>', schema: {}}},
    context_management: {edits: [{type: '<string>', keep: '<string>'}]},
    metadata: {},
    flagged_categories: []
  })
};

fetch('https://api.example.com/v1/messages', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "content": [
    {}
  ],
  "model": "<string>",
  "usage": {
    "input_tokens": 1,
    "output_tokens": 1,
    "cache_creation_input_tokens": 1,
    "cache_read_input_tokens": 1
  },
  "type": "message",
  "role": "assistant",
  "stop_sequence": "<string>"
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

Headers

Authorization

string | null

Bearer API key.

x-api-key

string | null

API key alternative for Anthropic-compatible clients. Authorization takes precedence when both headers are present.

Body

application/json

Anthropic Messages-compatible request.

model

string

required

Minimum string length: 1

max_tokens

integer

required

Required range: 1 <= x <= 999990

messages

AnthropicMessage · object[]

required

Minimum array length: 1

Show child attributes

system

stream

boolean

default:false

temperature

number | null

Required range: 0 <= x <= 1

top_p

number | null

Required range: 0 <= x <= 1

top_k

integer | null

Required range: x >= 0

stop_sequences

string[] | null

tools

Tools · object[] | null

tool_choice

AnthropicToolChoice · object | null

Show child attributes

thinking

AnthropicThinking · object | null

Show child attributes

output_config

AnthropicOutputConfig · object | null

Show child attributes

context_management

AnthropicContextManagement · object | null

Supported beta context-management subset.

keep=all does not remove any replayed thinking blocks, so it can be safely consumed at the compatibility boundary and omitted from the vLLM provider payload.

Show child attributes

metadata

Metadata · object | null

service_tier

enum<string> | null

Available options:

auto,

standard_only

flagged_categories

enum<string>[]

Available options:

harassment,

harassment/threatening,

hate,

hate/threatening,

illicit,

illicit/violent,

self-harm,

self-harm/intent,

self-harm/instructions,

sexual,

sexual/minors,

violence,

violence/graphic

Response

Successful Response

string

required

Pattern: ^msg_

content

Content · object[]

required

model

string

required

stop_reason

enum<string> | null

required

Available options:

end_turn,

max_tokens,

stop_sequence,

tool_use

usage

AnthropicUsage · object

required

Show child attributes

type

string

default:message

Allowed value: "message"

role

string

default:assistant

Allowed value: "assistant"

stop_sequence

string | null

Last modified on August 11, 2026

Create an Anthropic Messages-compatible response

curl --request POST \
  --url https://api.example.com/v1/messages \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "max_tokens": 499995,
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "system": "<string>",
  "stream": false,
  "temperature": 0.5,
  "top_p": 0.5,
  "top_k": 1,
  "stop_sequences": [
    "<string>"
  ],
  "tools": [
    {}
  ],
  "tool_choice": {
    "name": "<string>",
    "disable_parallel_tool_use": true
  },
  "thinking": {
    "budget_tokens": 499995
  },
  "output_config": {
    "format": {
      "type": "<string>",
      "schema": {}
    }
  },
  "context_management": {
    "edits": [
      {
        "type": "<string>",
        "keep": "<string>"
      }
    ]
  },
  "metadata": {},
  "flagged_categories": []
}
'

import requests

url = "https://api.example.com/v1/messages"

payload = {
    "model": "<string>",
    "max_tokens": 499995,
    "messages": [{ "content": "<string>" }],
    "system": "<string>",
    "stream": False,
    "temperature": 0.5,
    "top_p": 0.5,
    "top_k": 1,
    "stop_sequences": ["<string>"],
    "tools": [{}],
    "tool_choice": {
        "name": "<string>",
        "disable_parallel_tool_use": True
    },
    "thinking": { "budget_tokens": 499995 },
    "output_config": { "format": {
            "type": "<string>",
            "schema": {}
        } },
    "context_management": { "edits": [
            {
                "type": "<string>",
                "keep": "<string>"
            }
        ] },
    "metadata": {},
    "flagged_categories": []
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    max_tokens: 499995,
    messages: [{content: '<string>'}],
    system: '<string>',
    stream: false,
    temperature: 0.5,
    top_p: 0.5,
    top_k: 1,
    stop_sequences: ['<string>'],
    tools: [{}],
    tool_choice: {name: '<string>', disable_parallel_tool_use: true},
    thinking: {budget_tokens: 499995},
    output_config: {format: {type: '<string>', schema: {}}},
    context_management: {edits: [{type: '<string>', keep: '<string>'}]},
    metadata: {},
    flagged_categories: []
  })
};

fetch('https://api.example.com/v1/messages', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "content": [
    {}
  ],
  "model": "<string>",
  "usage": {
    "input_tokens": 1,
    "output_tokens": 1,
    "cache_creation_input_tokens": 1,
    "cache_read_input_tokens": 1
  },
  "type": "message",
  "role": "assistant",
  "stop_sequence": "<string>"
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}