API Reference

Anthropic Messages

POST https://api.tu-zi.com/v1/messages

Preview guide

Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.

# Anthropic Messages

Anthropic Messages

## Endpoint and authentication

`POST https://api.tu-zi.com/v1/messages`

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

```http
Authorization: Bearer YOUR_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json
```

## Body parameters

| Field | Type | Required | Description / constraints |
| --- | --- | --- | --- |
| model | string | Yes | Model name to call. Example: claude-3-7-sonnet |
| max_tokens | number | Yes | Required explicit Anthropic output token limit. Small limits can truncate output; larger limits may increase maximum time and cost without forcing longer output. Form initial value (not an upstream default): 512 Range in this definition: 1 ~ 128000 Example: 512 |
| messages | array | Yes | Conversation messages; content supports structured text blocks and other supported block types. Example: [{"role":"user","content":"你好"}] |
| stream | boolean | No | Whether to enable streaming responses. Form initial value (not an upstream default): false Example: false |
| temperature | number | No | Sampling temperature between 0 and 1. Form initial value (not an upstream default): 0.7 Range in this definition: 0 ~ 1 Example: 0.7 |
| top_p | number | No | Nucleus sampling probability threshold. Form initial value (not an upstream default): 1 Range in this definition: 0 ~ 1 Example: 0.9 |
| top_k | number | No | Sample only from the K most probable tokens. Range in this definition: 1 ~ 500 Example: 40 |
| messages[].role | string | No | user or assistant. System instructions belong in top-level system. |
| messages[].content | string \| array | No | Text or text/image/tool_use/tool_result blocks. |
| tools | array | No | Tool definitions contain name, description and input_schema. |

## Minimal request example

```json
{
  "model": "YOUR_MODEL",
  "max_tokens": 512,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}
```

## Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

## Code examples

### curl

```bash
curl --request POST 'https://api.tu-zi.com/v1/messages' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'anthropic-version: 2023-06-01' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "YOUR_MODEL",
  "max_tokens": 512,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'
```

### python

```python
import json
import os
import requests

url = "https://api.tu-zi.com/v1/messages"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\",\"anthropic-version\":\"2023-06-01\",\"Content-Type\":\"application/json\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
payload = json.loads("{\"model\":\"YOUR_MODEL\",\"max_tokens\":512,\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}")
response = requests.request("POST", url, headers=headers, json=payload, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.
```

### javascript

```javascript
// Node.js 20+
const url = "https://api.tu-zi.com/v1/messages";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "anthropic-version": "2023-06-01",
  "Content-Type": "application/json"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify({
  "model": "YOUR_MODEL",
  "max_tokens": 512,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}) });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.
```

## Response fields

| Field | Type | Description / constraints |
| --- | --- | --- |
| content[] | object | Content blocks such as text and tool_use. |
| stop_reason | string | Stop reason. |
| usage | object | input_tokens and output_tokens. |

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

```json
{
  "id": "msg_example",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 5,
    "output_tokens": 1
  }
}
```

## Streaming

With stream=true handle message_start, content_block_delta, message_delta and message_stop SSE events.

## Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

## Constraints

This page describes the base protocol. Use the selected model quick start for supported fields, enums, limits and asynchronous behavior. Replace YOUR_MODEL. Form initial values are not upstream defaults.

## Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-anthropic

Related protocol guide: https://api.tu-zi.com/docs/api/anthropic

This export contains documentation and examples only, without real credentials, account data or user requests.

Updated 2026-11-02 · Reviewed 2026-11-02

Endpoint and authentication

POST https://api.tu-zi.com/v1/messages

Transport: json

Use an inference API key. Examples contain placeholders; read credentials from environment variables.

Authorization: Bearer YOUR_API_KEY
anthropic-version: 2023-06-01
Content-Type: application/json

Minimal request example

{
  "model": "YOUR_MODEL",
  "max_tokens": 512,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}

Before running

Replace https://api.tu-zi.com with this site origin (do not append /v1 twice), and YOUR_MODEL with the exact marketplace model ID. Install requests for Python; use Node.js 20+ and save JavaScript as .mjs. WebSocket samples list their own dependencies.

Create an inference key on the site and set API_KEY in the environment; replace YOUR_API_KEY in cURL. Prepare local input.png/input.wav files for upload examples.

Start with a minimal request, then read the result using the response fields below. For async APIs, a returned task ID requires polling; acceptance does not mean generation has finished.

Constraints

This page describes the base protocol. Use the selected model quick start for supported fields, enums, limits and asynchronous behavior. Replace YOUR_MODEL. Form initial values are not upstream defaults.

Body parameters

Field	Type	Required	Description / constraints
model	string	Yes	Model name to call. Example: claude-3-7-sonnet
max_tokens	number	Yes	Required explicit Anthropic output token limit. Small limits can truncate output; larger limits may increase maximum time and cost without forcing longer output. Form initial value (not an upstream default): 512 Range in this definition: 1 ~ 128000 Example: 512
messages	array	Yes	Conversation messages; content supports structured text blocks and other supported block types. Example: [{"role":"user","content":"你好"}]
stream	boolean	No	Whether to enable streaming responses. Form initial value (not an upstream default): false Example: false
temperature	number	No	Sampling temperature between 0 and 1. Form initial value (not an upstream default): 0.7 Range in this definition: 0 ~ 1 Example: 0.7
top_p	number	No	Nucleus sampling probability threshold. Form initial value (not an upstream default): 1 Range in this definition: 0 ~ 1 Example: 0.9
top_k	number	No	Sample only from the K most probable tokens. Range in this definition: 1 ~ 500 Example: 40
messages[].role	string	No	user or assistant. System instructions belong in top-level system.
messages[].content	string \| array	No	Text or text/image/tool_use/tool_result blocks.
tools	array	No	Tool definitions contain name, description and input_schema.

Response fields

Field	Type	Description / constraints
content[]	object	Content blocks such as text and tool_use.
stop_reason	string	Stop reason.
usage	object	input_tokens and output_tokens.

Illustrative response; some endpoints show essential fields only. Optional fields may be absent.

{
  "id": "msg_example",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 5,
    "output_tokens": 1
  }
}

Streaming

With stream=true handle message_start, content_block_delta, message_delta and message_stop SSE events.

Errors and retries

Check HTTP status and protocol-specific errors; do not mix error formats across protocols. For 401/403 check credentials and permissions, for 429 back off, and for 5xx check gateway/upstream status. Error bodies may contain error/message/code depending on the protocol.

Use bounded exponential backoff for reads. Do not blindly retry task creation, generation, or key mutations, to avoid duplicate billing or execution.

Document information and sources

Documentation source

Definition version: 1

Reviewed: 2026-11-02

Source: https://api.tu-zi.com/en/docs/api/reference-relay-anthropic

Related protocol guide: https://api.tu-zi.com/docs/api/anthropic

This export contains documentation and examples only, without real credentials, account data or user requests.

Request examples

curl --request POST 'https://api.tu-zi.com/v1/messages' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'anthropic-version: 2023-06-01' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "YOUR_MODEL",
  "max_tokens": 512,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

import json
import os
import requests

url = "https://api.tu-zi.com/v1/messages"
headers = json.loads("{\"Authorization\":\"Bearer YOUR_API_KEY\",\"anthropic-version\":\"2023-06-01\",\"Content-Type\":\"application/json\"}")
headers["Authorization"] = "Bearer " + os.environ["API_KEY"]
payload = json.loads("{\"model\":\"YOUR_MODEL\",\"max_tokens\":512,\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}")
response = requests.request("POST", url, headers=headers, json=payload, timeout=120)
response.raise_for_status()
result = response.json()
if isinstance(result, dict) and (result.get("success") is False or result.get("error")):
    raise RuntimeError(json.dumps(result, ensure_ascii=False))
print(result)  # Also inspect protocol-specific status/code fields.

// Node.js 20+
const url = "https://api.tu-zi.com/v1/messages";
const headers = {
  "Authorization": "Bearer YOUR_API_KEY",
  "anthropic-version": "2023-06-01",
  "Content-Type": "application/json"
};
headers.Authorization = 'Bearer ' + process.env.API_KEY;
const response = await fetch(url, { method: "POST", headers, body: JSON.stringify({
  "model": "YOUR_MODEL",
  "max_tokens": 512,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}) });
if (!response.ok) throw new Error(await response.text());
const result = await response.json();
if (result?.success === false || result?.error) throw new Error(JSON.stringify(result));
console.log(result); // Also inspect protocol-specific status/code fields.