Claude Messages API

Fully compatible with Claude Messages API format

POST /v1/messages

Claude Messages API

cURL

curl --request POST \
  --url https://api.poyo.ai/v1/messages \
  --header 'Content-Type: application/json' \
  --header 'anthropic-version: <api-key>' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Rewrite the following product announcement to be more gentle and user-friendly: We will have maintenance for 2 hours this weekend, services will be unavailable during this time."
    }
  ]
}
'

200

{
  "code": 200,
  "data": {
    "id": "msg_013zva2CMHNLnXJNN3QKQ2EF",
    "type": "message",
    "role": "assistant",
    "content": [
      {
        "type": "text",
        "text": "Hello! I'm Claude. Nice to meet you."
      }
    ],
    "model": "claude-sonnet-4-5-20250929",
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "usage": {
      "input_tokens": 10,
      "output_tokens": 13
    }
  }
}

• Fully compatible with Claude Messages API format
• Supports multi-turn conversations and single queries
• Supports multimodal content including text and images

Authorizations

x-api-key · string · required

API key for authentication

Visit the API Key Management Page to get your API Key

Add to the request header:

x-api-key: PoYo_API_KEY

anthropic-version · string · required

API version

Example: 2025-10-01

Body

model · string · required

Model name. Example: claude-sonnet-4-5-20250929

messages · array · required

List of conversation messages

Show Message object structure

role · enum<string> · required

Role type

• user - User message
• assistant - AI response (for multi-turn)

content · string · required

Message content

Your question or message

Example:

[{"role": "user", "content": "Summarize the purpose of feature canary releases in two sentences."}]

Multi-turn conversation:

[
  {"role": "user", "content": "Help me polish this sentence: This feature is still in testing."},
  {"role": "assistant", "content": "How about: This feature is currently in internal beta testing."},
  {"role": "user", "content": "Give me a more formal version."}
]

max_tokens · integer · required

Maximum number of tokens to generate

system · string or array

System prompt (string or structured blocks)

String example:

"You are a product announcement editor, keep it objective and concise."

Structured example:

[{"type": "text", "text": "You are a product announcement editor, keep it objective and concise."}]

temperature · number

Controls output randomness, range 0-1

top_p · number

Nucleus sampling parameter, range 0-1

top_k · integer

Top-k sampling parameter

stream · boolean

Whether to use streaming output

stop_sequences · array

Stop sequences where generation stops

metadata · object

Additional metadata such as user_id

tools · array

Tool definitions available to the model

[
  {
    "name": "get_weather",
    "description": "Get weather by city",
    "input_schema": {
      "type": "object",
      "properties": {
        "city": {"type": "string"}
      },
      "required": ["city"]
    }
  }
]

tool_choice · string or object

Controls tool usage behavior

Examples: "auto", {"type": "tool", "name": "get_weather"}

Response

id · string

Unique identifier for the response

type · string

Object type, fixed as message

role · string

Role type, fixed as assistant

content · array

Content blocks

Show Properties

type · string

Block type (e.g., text)

text · string

Text content

model · string

The actual model name used

stop_reason · string

Reason for completion

stop_sequence · string

Stop sequence that triggered completion (if any)

usage · object

Token usage statistics

Show Properties

input_tokens · integer

Number of tokens in the input messages

output_tokens · integer

Number of tokens in the generated content

Usage Examples

Basic Conversation

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 256,
  "messages": [
    {"role": "user", "content": "Explain the meaning of 'rate limiting' in three sentences."}
  ]
}

Streaming Response

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 256,
  "stream": true,
  "messages": [
    {"role": "user", "content": "Write a product update announcement under 80 words, professional yet friendly."}
  ]
}

Tool Use

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 256,
  "tools": [
    {
      "name": "get_weather",
      "description": "Get weather by city",
      "input_schema": {
        "type": "object",
        "properties": {
          "city": {"type": "string"}
        },
        "required": ["city"]
      }
    }
  ],
  "tool_choice": "auto",
  "messages": [
    {"role": "user", "content": "Check the weather in Tokyo and provide a one-sentence travel suggestion."}
  ]
}

Vision Understanding

{
  "model": "claude-sonnet-4-5-20250929",
  "max_tokens": 256,
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "Describe the main subject and scene in the image, and provide an alt text for it."},
        {
          "type": "image",
          "source": {
            "type": "base64",
            "media_type": "image/png",
            "data": "BASE64_IMAGE_DATA"
          }
        }
      ]
    }
  ]
}

Authorizations

x-api-key · string · header · required

API key for authentication.

Visit the API Key Management Page to get your API Key

Add to the request header:

x-api-key: YOUR_API_KEY

anthropic-version · string · header · required

API version. Example: 2025-10-01.

Body

application/json

model · string · required

Claude model name.

Example:

"claude-sonnet-4-5-20250929"

messages · object[] · required

Conversation messages in order. Example: [{"role": "user", "content": "Summarize the purpose of feature canary releases in two sentences."}].

Show child attributes

max_tokens · integer · required

Maximum tokens to generate.

Required range: x >= 1

Example:

1024

system · string object[]

System prompt for the assistant.

Example:

"You are a product announcement editor, keep it objective and concise."

temperature · number

Sampling temperature. Higher values are more random.

Required range: 0 <= x <= 1

Example:

1

top_p · number

Nucleus sampling parameter. Higher values are more random.

Required range: 0 <= x <= 1

Example:

1

top_k · integer

Top-k sampling parameter.

Required range: x >= 1

Example:

40

stream · boolean

Enable streaming responses.

Example:

false

stop_sequences · string[]

Stop sequences. The model stops when it encounters any of these strings.

metadata · object

Additional metadata such as user_id.

tools · object[]

Tool definitions available to the model.

Show child attributes

tool_choice · string object

Controls tool usage behavior.

Example:

"auto"

Response

200 - application/json

Message created

code · integer

Example:

200

data · object

Show child attributes