> ## Documentation Index
> Fetch the complete documentation index at: https://mixroute.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT 6.1 Terra

> Fast, efficient OpenAI model for visual reasoning, screen-based workflows, and clear writing, with text and image input.

GPT 6.1 Terra is suited to interpreting product images and technical drawings, drafting text, and focused coding tasks. It is a separate model from GPT 5.6 Terra and GPT 6.1 Sol.

## Model Information

| Field | Description |
| - | - |
| Model ID | `gpt-6.1-terra` |
| Context window | 1,050,000 tokens |
| Maximum output | 128,000 tokens |
| Input | Text and images; no native audio or video input. |
| Output | Text, including structured output through compatible endpoints. |

> [!NOTE]
>
> The sizes above are provider specifications. Effective limits, availability, pricing, Responses access, and hosted tools depend on the MixRoute route; model availability alone does not enable every upstream tool.

## Reasoning and Tool Calling

Supported effort levels are `none`, `low`, `medium` (default), `high`, `xhigh`, and `max`. `none` disables reasoning; `minimal` is not a supported level for this model.

Use top-level `reasoning_effort` in Chat Completions and nested `reasoning.effort` in Responses.

> [!WARNING]
>
> Tool calling requires Responses, even when reasoning is set to `none`. Do not attach `tools` or `tool_choice` to this model in Chat Completions. For tool workflows, use a route that supports Responses.

When effort is not `none`, omit `temperature`, `top_p`, and `top_logprobs`; also omit Chat Completions `logprobs` and Responses `include: ["message.output_text.logprobs"]`.

## Chat Completions Examples

Set `MIXROUTE_API_KEY` to your MixRoute API key. These examples use `low` effort without tools.

**cURL**

```bash theme={null}
curl "https://api.mixroute.ai/v1/chat/completions" \
  -H "Authorization: Bearer $MIXROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6.1-terra",
    "messages": [{"role": "user", "content": "Draft a concise status update for a software project."}],
    "reasoning_effort": "low",
    "max_completion_tokens": 2048
  }'
```

**Python**

```python theme={null}
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["MIXROUTE_API_KEY"],
    base_url="https://api.mixroute.ai/v1",
)
response = client.chat.completions.create(
    model="gpt-6.1-terra",
    messages=[{"role": "user", "content": "Draft a concise status update for a software project."}],
    reasoning_effort="low",
    max_completion_tokens=2048,
)
print(response.choices[0].message.content)
```

## Request Fields

| Parameter | Required | Description |
| - | - | - |
| `model` | Yes | Use `gpt-6.1-terra`. |
| `messages` | Yes | Conversation messages containing `role` and `content`. |
| `reasoning_effort` | No | none / low / medium / high / xhigh / max; default medium. |
| `max_completion_tokens` | No | Budget covering reasoning and visible output tokens, subject to the model and route limits. |
| `stream` | No | Set true for SSE streaming; use `choices[0].delta.content` for text chunks. |

## Responses Integration

On a MixRoute route with Responses support, use `input`, `reasoning.effort`, and `max_output_tokens` instead of the Chat Completions fields:

```bash theme={null}
curl "https://api.mixroute.ai/v1/responses" \
  -H "Authorization: Bearer $MIXROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6.1-terra",
    "input": "Draft a concise status update for a software project.",
    "reasoning": {"effort": "low"},
    "max_output_tokens": 2048,
    "store": false
  }'
```

Responses function tools use top-level `name`, `description`, and `parameters`, not a nested `function` object. Your application executes returned calls and sends `function_call_output` with the matching `call_id`.

Preserve all returned output items required for the next turn, including reasoning items. Hosted computer-use and other tools need separate route support and application integration; changing the model ID alone does not enable them.

[Chat Completions reference](https://mixroute.ai/docs/api-reference/endpoint/chat-openai.md) · [Responses reference](https://mixroute.ai/docs/api-reference/endpoint/responses-openai.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.