# OpenRouter APIs — Google: Gemini 3.5 Transcribe (google/gemini-3.5-transcribe)

Guide for calling every confirmed OpenRouter API that serves `google/gemini-3.5-transcribe`.

Model page: https://openrouter.ai/google/gemini-3.5-transcribe
Create an API key: https://openrouter.ai/settings/keys

## Pricing

Standard-variant prices for `google/gemini-3.5-transcribe`, per provider, in the unit each provider bills (tokens, images, seconds of video, or characters of audio). Pay-as-you-go with no markup on the provider's price.

- Google AI Studio: $2/M tokens input, $12/M tokens output

Full price table, including other variants and per-request charges: https://openrouter.ai/google/gemini-3.5-transcribe
How OpenRouter prices requests: https://openrouter.ai/pricing

## EU in-region routing

`google/gemini-3.5-transcribe` is not currently available through EU in-region routing.

Docs: https://openrouter.ai/docs/guides/features/in-region-routing

## Authentication

Send this header with every request:

- Authorization: Bearer $OPENROUTER_API_KEY

## Speech-to-Text API

Transcribe audio with `google/gemini-3.5-transcribe` through OpenRouter's Speech-to-Text API.

Docs: https://openrouter.ai/docs/api/api-reference/stt/create-transcription

### Endpoint

POST https://openrouter.ai/api/v1/audio/transcriptions

Headers:
- Content-Type: application/json

### Request fields (google/gemini-3.5-transcribe)

- model: string (required) — `"google/gemini-3.5-transcribe"`
- input_audio: object (required) — `{ "data": "<base64 bytes>", "format": "wav" }`

### Response

The default response is JSON containing the transcript and usage:

```json
{
  "text": "Hello, this is a transcription.",
  "usage": { "seconds": 9.2, "total_tokens": 113, "cost": 0.000508 }
}
```

`response_format: "verbose_json"` can additionally return language, duration, segments, and
word timestamps when the routed provider supports them.

### Examples

#### Transcribe an audio file

```bash
# Base64-encode your audio file
    AUDIO_BASE64=$(base64 < audio.wav | tr -d '\n')

    curl https://openrouter.ai/api/v1/audio/transcriptions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $OPENROUTER_API_KEY" \
      -d '{
        "model": "google/gemini-3.5-transcribe",
        "input_audio": {
          "data": "'"$AUDIO_BASE64"'",
          "format": "wav"
        }
      }'
```

### Error differences

- 400 — malformed audio input or an audio option the routed provider does not support
- 502 — the upstream audio operation failed

## Errors

Failures return `{"error": {"code": <number>, "message": <string>}}` with the HTTP status:

- 400 — malformed request or an unsupported parameter
- 401 — missing or invalid API key
- 402 — insufficient credits
- 403 — spend limit reached, key disabled, or access blocked
- 404 — unknown model or no provider can serve the request
- 429 — rate limited; retry with backoff
- 502 — the operation failed upstream; failed generations are not billed

---

Canonical version of this document: https://openrouter.ai/google/gemini-3.5-transcribe/llms.txt