# Create a message (Anthropic Messages compatibility)

`POST /v1/messages`

Anthropic Messages API compatibility endpoint. Accepts Anthropic-format requests and returns Anthropic-format responses. Supports tools, system prompts, and streaming. Authenticate with either Authorization: Bearer or x-api-key header.

## Authentication

Send `Authorization: Bearer $KOSCOMPUTE_API_KEY`.

## Request

Content type: `application/json`

| Field | Type | Required | Description |
|---|---|---:|---|
| `model` | string | Yes | See the endpoint guide for behavior and model support. |
| `messages` | array | Yes | See the endpoint guide for behavior and model support. |
| `max_tokens` | integer | Yes | See the endpoint guide for behavior and model support. |
| `system` | string · array | 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. |
| `top_k` | integer | No | See the endpoint guide for behavior and model support. |
| `stop_sequences` | array | No | See the endpoint guide for behavior and model support. |
| `tools` | array | No | See the endpoint guide for behavior and model support. |
| `tool_choice` | object | No | See the endpoint guide for behavior and model support. |
| `metadata` | object | No | See the endpoint guide for behavior and model support. |

## Examples

### cURL

```bash
curl https://api.koscompute.com/v1/messages \
  -H "x-api-key: $KOSCOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","max_tokens":120,"messages":[{"role":"user","content":"Reply with one sentence."}]}'
```

### Python

```python
import os
import requests

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

### JavaScript

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

## Responses

| Status | Meaning |
|---:|---|
| `200` | Successful response |
| `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 |
| `529` | Anthropic-compatible provider unavailable or upstream failure |

## Next steps

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