# Create a response

`POST /v1/responses`

Stateless, zero-data-retention Responses API compatibility for text generation. Supports message input, streaming SSE, local function tools, structured text formats, and model-dependent reasoning controls. store=true and non-null previous_response_id are rejected; clients must resend conversation context in input.

## Authentication

Send `Authorization: Bearer $KOSCOMPUTE_API_KEY`.

## Request

Content type: `application/json`

| Field | Type | Required | Description |
|---|---|---:|---|
| `model` | string | Yes | Public model ID returned by GET /models |
| `input` | string · array | Yes | See the endpoint guide for behavior and model support. |
| `stream` | boolean | No | See the endpoint guide for behavior and model support. |
| `temperature` | number | No | See the endpoint guide for behavior and model support. |
| `top_p` | number | No | See the endpoint guide for behavior and model support. |
| `max_output_tokens` | integer | No | See the endpoint guide for behavior and model support. |
| `tools` | array | No | See the endpoint guide for behavior and model support. |
| `tool_choice` | string · object | No | See the endpoint guide for behavior and model support. |
| `parallel_tool_calls` | boolean | No | See the endpoint guide for behavior and model support. |
| `text` | object | No | See the endpoint guide for behavior and model support. |
| `reasoning` | object | No | Model-dependent reasoning controls; public reasoning text is not exposed. |
| `metadata` | object | No | See the endpoint guide for behavior and model support. |
| `store` | boolean | No | Values: `False`. |
| `previous_response_id` | null | No | See the endpoint guide for behavior and model support. |
| `prompt_cache_key` | null | No | See the endpoint guide for behavior and model support. |

## Examples

### cURL

```bash
curl https://api.koscompute.com/v1/responses \
  -H "Authorization: Bearer $KOSCOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","input":"Reply with one sentence.","max_output_tokens":120}'
```

### Python

```python
import os
import requests

response = requests.post(
    "https://api.koscompute.com/v1/responses",
    headers={"Authorization": f"Bearer {os.environ['KOSCOMPUTE_API_KEY']}"},
    json={
  "model": "qwen/qwen3.8-27b",
  "input": "Reply with one sentence.",
  "max_output_tokens": 120
},
)
print(response.json())
```

### JavaScript

```javascript
const response = await fetch("https://api.koscompute.com/v1/responses", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.KOSCOMPUTE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({"model":"qwen/qwen3.8-27b","input":"Reply with one sentence.","max_output_tokens":120}),
});
console.log(await response.json());
```

## Responses

| Status | Meaning |
|---:|---|
| `200` | Completed JSON response or a canonical Responses SSE stream when stream=true |
| `400` | Bad request — invalid parameters or payload |
| `401` | Invalid or missing API key |
| `403` | Model not allowed for this API key |
| `404` | Public model not found |
| `413` | Request body exceeds the limit |
| `429` | Rate limit or admission capacity is full. The message states when to retry; vision saturation also reports active/total vision concurrency. |
| `500` | Internal server error |
| `502` | Invalid or failed upstream response |
| `503` | No healthy route |
| `504` | Backend generation timeout |

## Next steps

Use the endpoint guide for complete workflows, model capability notes, streaming behavior, and retry advice.