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

# GPT-6.1 Terra

> Use GPT-6.1 Terra through AnyFast for visual reasoning, computer use, and clear writing.

GPT-6.1 Terra is OpenAI's fast, efficient model for visual reasoning, precise computer use, and clear writing. Use the model ID `gpt-6.1-terra` with the OpenAI-compatible Responses API at `POST /v1/responses` or Chat Completions at `POST /v1/chat/completions`.

> [!NOTE]
>
> Prefer the Responses API for function calling with reasoning, Structured Outputs, and prompt caching. AnyFast accepted basic Chat Completions text requests, but a Chat Completions function call at `reasoning_effort: "low"` returned `404 DeploymentNotFound`.

## Model specifications

| Property | Value |
| - | - |
| Model ID | `gpt-6.1-terra` |
| Recommended API | Responses API |
| Input | Text and image |
| Output | Text |
| Context window (official specification) | 1,050,000 tokens |
| Maximum output | 128,000 tokens |
| Knowledge cutoff | June 1, 2026 |
| Reasoning effort | `none`, `low`, `medium`, `high`, `xhigh`, `max` |
| Default reasoning effort | `medium` |
| Fine-tuning | Not supported |

## When to use GPT-6.1 Terra

* Match product photos to catalog entries or interpret technical drawings.
* Work with application screens in a defined computer-use workflow.
* Draft and revise concise, natural text.
* Handle scoped code fixes with clear acceptance criteria.
* Analyze text and image inputs together.
* Produce JSON that follows a strict schema.

## Quick start

**Responses API**

```bash cURL theme={null}
curl https://www.anyfast.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6.1-terra",
    "input": "Summarize the key differences between these two product descriptions.",
    "reasoning": { "effort": "medium" },
    "max_output_tokens": 1024
  }'
```

**Chat Completions**

```bash cURL theme={null}
curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6.1-terra",
    "messages": [
      { "role": "user", "content": "Summarize this product description." }
    ],
    "reasoning_effort": "medium",
    "max_completion_tokens": 1024
  }'
```

## Tool calling

Use the Responses API when the model needs to reason and call tools:

```bash cURL theme={null}
curl https://www.anyfast.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6.1-terra",
    "input": "Call get_weather for Paris.",
    "reasoning": { "effort": "medium" },
    "tools": [{
      "type": "function",
      "name": "get_weather",
      "description": "Get the weather for a city.",
      "parameters": {
        "type": "object",
        "properties": {
          "city": { "type": "string" }
        },
        "required": ["city"],
        "additionalProperties": false
      },
      "strict": true
    }],
    "tool_choice": "required"
  }'
```

> [!WARNING]
>
> A tested AnyFast Responses request returned a `function_call` item with `name`, `arguments`, and `call_id`. A Chat Completions function call at `reasoning_effort: "low"` returned `404 DeploymentNotFound`; use Responses for tools.

## Reasoning and sampling rules

| Effort | Typical use |
| - | - |
| `none` | Simple tasks that do not need reasoning |
| `low` | Routine tasks with light reasoning |
| `medium` | General visual analysis and writing; the default |
| `high` | More difficult multi-step tasks |
| `xhigh` | Demanding visual or computer-use workflows |
| `max` | Maximum reasoning depth |

> [!WARNING]
>
> AnyFast accepted all six reasoning efforts through Responses. At `medium` effort, `temperature: 0.5` returned HTTP 400 with `error.param: "temperature"`. When reasoning effort is not `none`, omit `temperature`, `top_p`, and `top_logprobs`. For Chat Completions, also omit `logprobs`; for Responses, do not request `message.output_text.logprobs` in `include`.

## Core parameters

| Parameter | API | Description |
| - | - | - |
| `model` | Both | Must be `gpt-6.1-terra` |
| `input` | Responses | Text or ordered input items, including images |
| `messages` | Chat Completions | Ordered conversation messages |
| `reasoning.effort` | Responses | `none`, `low`, `medium`, `high`, `xhigh`, or `max`; all live-tested |
| `reasoning_effort` | Chat Completions | `medium` was live-tested for text requests |
| `max_output_tokens` | Responses | Maximum visible output and reasoning tokens, up to 128,000 |
| `max_completion_tokens` | Chat Completions | Maximum completion and reasoning tokens |
| `tools` | Responses | Top-level function tool definitions |
| `tool_choice` | Responses | `required` was live-tested with a function tool |
| `text.format` | Responses | Strict JSON Schema output succeeded in a live request |
| `prompt_cache_options.ttl` | Responses | `30m` was accepted; effective retention was not verified |
| `stream` | Both | Stream response events; both routes were live-tested |

> [!NOTE]
>
> In tested AnyFast Responses JSON, text appeared in `output[].content[].text` on `output_text` blocks, and function calls appeared as `output[]` items. The raw JSON had no top-level `output_text` field. A strict JSON Schema request succeeded. A `prompt_cache_options.ttl: "30m"` request returned `prompt_cache_retention: "24h"`; the short prompt wrote no cache entry. Chat Completions returned `model: "azure/gpt-6.1-terra"` and omitted `choices[].logprobs`.

> **[API Reference](https://docs.anyfast.ai/api-reference/model-api/openai/gpt-6.1-terra.md)**
>
> View the GPT-6.1 Terra API reference.

## Official references

* [GPT-6.1 Terra model page](https://developers.openai.com/api/docs/models/gpt-6.1-terra)
* [Using GPT-6](https://developers.openai.com/api/docs/guides/latest-model)


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