API Reference
OpenAI Responses Compact
Responses context compaction for existing conversations. Returns reusable output items and does not support streaming.
Preview guide
Paste into an AI assistant to help with integration. Documentation and examples only; no real credentials.
Updated · Reviewed
Endpoint and authentication
POST https://api.tu-zi.com/v1/responses/compact
Transport: json
Use an inference API key. Examples contain placeholders; read credentials from environment variables.
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
Minimal request example
{
"model": "YOUR_MODEL",
"input": [
{
"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
The example shows the response envelope only; output depends on context and channel. Preserve opaque compaction items without attempting to decrypt or rewrite them. This endpoint requires separate pricing for the model name plus -openai-compact. Availability of ordinary Responses does not imply Compact is configured.
Body parameters
| Field | Type | Required | Description / constraints |
|---|---|---|---|
| model | string | Yes | Model name to call. Example: gpt-4.1-mini |
| input | string | array | Yes | Input content. Example: 给我一个 3 点总结 |
| instructions | string | No | Instructions used during compaction. |
| previous_response_id | string | No | Previous response ID; requires channel support. |
Response fields
| Field | Type | Description / constraints |
|---|---|---|
| id | string | Compaction response ID. |
| object | string | Response object type. |
| created_at | integer | Creation timestamp in Unix seconds. |
| output | array | Compacted output items. Preserve their full structure for subsequent requests; not every item contains text. |
| usage | object | Compaction usage. |
| error | object | null | Error object on failure. |
Illustrative response; some endpoints show essential fields only. Optional fields may be absent.
{
"id": "cmp_example",
"object": "response.compaction",
"created_at": 1793491200,
"output": []
}
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.
兔子API