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

# GPT-5.4

> Call the gpt-5.4 text model through SnapGen-compatible text protocols.

Use `gpt-5.4` for OpenAI-compatible chat and streaming workloads. The same model ID also works with SnapGen's Responses, Anthropic Messages, and Gemini native compatibility routes.

| Property     | Value                         |
| ------------ | ----------------------------- |
| Model ID     | `gpt-5.4`                     |
| Input price  | \$1.25 per 1M tokens          |
| Output price | \$7.50 per 1M tokens          |
| Streaming    | Supported with `stream: true` |

<ParamField body="model" type="string" required>
  Set to `gpt-5.4`.
</ParamField>

<ParamField body="messages" type="array" required>
  Ordered system, user, and assistant messages.
</ParamField>

<ParamField body="stream" type="boolean" default="false">
  Set to `true` to receive server-sent events.
</ParamField>

## Request

```bash theme={null}
curl https://api.snapgen.org/v1/chat/completions \
  -H "Authorization: Bearer $SNAPGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [{"role": "user", "content": "Summarize this design decision in three bullets."}]
  }'
```

Read generated text from `choices[0].message.content`. See [Chat Completions protocol](/api-reference/chat-completions) for streaming and response fields.

## Compatible protocol paths

| Format             | Path                                     |
| ------------------ | ---------------------------------------- |
| Chat Completions   | `/v1/chat/completions`                   |
| Responses          | `/v1/responses`                          |
| Anthropic Messages | `/v1/messages`                           |
| Gemini native      | `/v1beta/models/gpt-5.4:generateContent` |

<Note>
  Billing uses the normalized input and output token counts returned by the
  gateway. Confirm live rates on the [models page](https://snapgen.org/models).
</Note>