# GPT-5.6 Terra API

OpenAI GPT-5.6 Terra: mid GPT-5.6 tier balancing quality and cost.

Base URL: https://01router.com/api/v1
Model ID: gpt-5.6-terra
Documentation: https://01router.com/gateway/gpt-5.6-terra#api

## Quick start

Set API_KEY to your project key, then run a sample from your server. Replace example media URLs with your own public URLs.

```bash
export API_KEY="YOUR_API_KEY"
curl "https://01router.com/api/v1/chat/completions" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'JSON'
{
  "model": "gpt-5.6-terra",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false
}
JSON
```

## Endpoints

| Method | Path | Authentication | Description |
| --- | --- | --- | --- |
| POST | /api/v1/chat/completions | API key required | Chat completion (OpenAI-compatible, stream or not) |
| GET | /api/v1/models/gpt-5.6-terra | Public · no key | Get one model |

## Authentication

Send your API key as a Bearer token. Requests are billed to the key owner's credits.

`Authorization: Bearer <API_KEY>`

## Input

Send messages directly in the request body. Chat requests do not use an input wrapper.

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| model | string | Yes | "gpt-5.6-terra" |
| provider | string | No | Pin a provider; omit to auto-route to the cheapest. One of: replicate \| wavespeed \| kie \| apimart \| evolink \| atlascloud \| vercel \| openrouter |
| messages | object[] | Yes | OpenAI-format messages, each with role and content. |
| stream | boolean | No | true returns an SSE stream. |
| max_tokens | integer | No | Output token cap; credits are pre-held for it (default 4096). |

## Output

This example uses stream: false. Read the reply from choices[0].message.content. With stream: true, read SSE chunks from choices[].delta until [DONE].

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| id | string | Yes | Chat completion ID |
| object | string | Yes | chat.completion |
| model | string | Yes | gpt-5.6-terra |
| choices | object[] | Yes | Reply choices; message.content contains the non-streaming response. |
| usage | object | No | Token usage: prompt_tokens, completion_tokens and total_tokens. Availability depends on the provider. |

### Task completed

```json
{
  "id": "chatcmpl-example",
  "object": "chat.completion",
  "model": "gpt-5.6-terra",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 8,
    "total_tokens": 17
  }
}
```

## Errors

Check the HTTP status and error.message. Fix the request before retrying validation or authentication errors. A failed generation is reported in status and error on the task itself.

```json
{
  "error": {
    "message": "Invalid or missing API key",
    "code": "unauthorized"
  }
}
```

HTTP 400: invalid request; 401: unauthorized; 402: insufficient credits; 404: not found; 409: not cancelable; 429: rate/concurrency/quota limit; 5xx: upstream/server error.

Full API reference: https://01router.com/docs/errors