> ## 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-5.4 Mini

> OpenAI's GPT-5.4 Mini — faster, more efficient GPT-5.4 variant for coding, computer use, and subagents.

GPT-5.4 Mini is available through Anyfast via the OpenAI Responses API (`/v1/responses`). It brings GPT-5.4 capabilities to a faster, lower-cost model for high-volume workloads.

## Key capabilities

* **Responses API** — Uses the newer `/v1/responses` endpoint with `input` instead of `messages`
* **Reasoning control** — Configure reasoning effort: none (default), low, medium, high, or xhigh
* **Coding and agents** — Optimized for coding, computer use, and subagent workloads
* **Long context** — Supports a 400K token context window and up to 128K output tokens
* **Multimodal input** — Accepts text and image input, with text output
* **Tool use** — Supports function calling and Responses API tools such as web search, file search, code interpreter, and computer use
* **Streaming** — Supports real-time token streaming via SSE

## Quick example

<CodeGroup>
  ```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-5.4-mini",
      "input": [
        { "role": "user", "content": "Explain quantum entanglement in simple terms." }
      ],
      "reasoning": {
        "effort": "medium",
        "summary": "auto"
      },
      "text": {
        "format": { "type": "text" },
        "verbosity": "medium"
      },
      "store": true
    }'
  ```

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

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  response = client.responses.create(
      model="gpt-5.4-mini",
      input=[
          {"role": "user", "content": "Explain quantum entanglement in simple terms."}
      ],
      reasoning={"effort": "medium", "summary": "auto"},
      text={"format": {"type": "text"}, "verbosity": "medium"},
      store=True
  )

  print(response.output[0].content[0].text)
  ```

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

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  stream = client.responses.create(
      model="gpt-5.4-mini",
      input=[
          {"role": "user", "content": "Write a short poem about the sea."}
      ],
      stream=True
  )

  for event in stream:
      if hasattr(event, 'delta'):
          print(event.delta, end="")
  ```
</CodeGroup>

## Parameters

| Parameter           | Type    | Required | Description                                                                                                      |
| ------------------- | ------- | -------- | ---------------------------------------------------------------------------------------------------------------- |
| `model`             | string  | Yes      | Must be `gpt-5.4-mini`                                                                                           |
| `input`             | array   | Yes      | List of `{ role, content }` objects                                                                              |
| `stream`            | boolean | No       | Enable SSE streaming. Default: `false`                                                                           |
| `top_p`             | float   | No       | Nucleus sampling threshold. Default: `1`                                                                         |
| `max_output_tokens` | integer | No       | Maximum output tokens to generate                                                                                |
| `reasoning`         | object  | No       | `{ effort, summary }` — controls reasoning depth. `effort` supports `none`, `low`, `medium`, `high`, and `xhigh` |
| `text`              | object  | No       | `{ format, verbosity }` — controls output format and verbosity                                                   |
| `tools`             | array   | No       | List of tools the model may call                                                                                 |
| `store`             | boolean | No       | Store response for later retrieval. Default: `true`                                                              |

<Card title="API Reference" icon="code" href="/api-reference/model-api/openai/gpt-5-4-mini">
  View the interactive API playground for GPT-5.4 Mini.
</Card>

<script src="/feedback.js" />