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

# GPT-5.4 mini

> 5.4-tier mini — the small model with 5.4's tighter tool-call generation. Drop-in cost-down from GPT-5.4.

**Vendor:** OpenAI
**Model ID:** `gpt-5-4-mini`
**Capability:** 128K context · tool use · vision · streaming · structured output
**Pricing:** per-token, mini tier ([live rate](https://bytespike.ai/pricing#text))

GPT-5.4-mini brings [GPT-5.4](/api-reference/text/gpt-5-4)'s tighter
structured output and tool-call argument generation to mini-tier
pricing. Right
default for production extraction and agent loops where you want 5.4's
quality bump without the standard-tier cost.

## Request

```bash theme={null}
curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gpt-5-4-mini",
    "messages": [{"role": "user", "content": "Extract the dollar amounts from this invoice."}],
    "response_format": {"type": "json_object"}
  }'
```

### Body parameters

| Field             | Type    | Required | Default   | Notes                      |
| ----------------- | ------- | -------- | --------- | -------------------------- |
| `model`           | string  | yes      | —         | `gpt-5-4-mini`             |
| `messages`        | array   | yes      | —         | —                          |
| `max_tokens`      | integer | no       | model max | Max: 16384.                |
| `tools`           | array   | no       | —         | Parallel function calling. |
| `response_format` | object  | no       | —         | JSON / structured output.  |
| `stream`          | boolean | no       | false     | SSE streaming.             |

## Response

```json theme={null}
{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "gpt-5-4-mini",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "{\"amounts\": [142.50, 89.00]}"}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 87, "completion_tokens": 24, "total_tokens": 111}
}
```

## Code examples

<CodeGroup>
  ```bash cURL theme={null}
  curl https://llm.bytespike.ai/v1/chat/completions \
    -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
    -H "content-type: application/json" \
    -d '{"model": "gpt-5-4-mini", "messages": [{"role": "user", "content": "Extract amounts as JSON."}], "response_format": {"type": "json_object"}}'
  ```

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

  client = OpenAI(base_url="https://llm.bytespike.ai/v1", api_key="$BYTESPIKE_API_KEY")
  resp = client.chat.completions.create(
      model="gpt-5-4-mini",
      messages=[{"role": "user", "content": "Extract amounts as JSON."}],
      response_format={"type": "json_object"},
  )
  print(resp.choices[0].message.content)
  ```

  ```javascript Node theme={null}
  import OpenAI from "openai"

  const client = new OpenAI({
    baseURL: "https://llm.bytespike.ai/v1",
    apiKey: process.env.BYTESPIKE_API_KEY,
  })
  const resp = await client.chat.completions.create({
    model: "gpt-5-4-mini",
    messages: [{ role: "user", content: "Extract amounts as JSON." }],
    response_format: { type: "json_object" },
  })
  console.log(resp.choices[0].message.content)
  ```
</CodeGroup>

## Streaming + caching

`"stream": true` for SSE. Automatic prompt caching.

## Errors

| Code                        | Trigger  | Billed?         |
| --------------------------- | -------- | --------------- |
| 400 / 401 / 402 / 422 / 429 | Standard | No              |
| 5xx                         | Upstream | No (auto-retry) |

## When to use

* Production extraction and structured output where 5-mini's quality plateaus.
* Tool-using agent steps where argument tightness matters.
* For more capability, see [GPT-5.4](/api-reference/text/gpt-5-4) or [GPT-5.5](/api-reference/text/gpt-5-5).

## Limits

| Limit                   | Value          |
| ----------------------- | -------------- |
| Context window          | 128K tokens    |
| Max output              | 16384 tokens   |
| Supports tool use       | Yes (parallel) |
| Supports vision         | Yes            |
| Supports streaming      | Yes            |
| Supports prompt caching | Automatic      |