# Gemini 2.5 Flash Native Audio (Live)

> Google Gemini 2.5 Flash real-time bidirectional voice model. Supports text and audio input/output. Provides low-latency voice conversations via Live API (WebSocket).

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `google/gemini-2.5-flash-native-audio`
- Status: stops working on 2026-11-17, use google/gemini-3.8-live instead
- Live status and providers as JSON, no key needed: https://api.ohmygpt.com/v1/models/google/gemini-2.5-flash-native-audio
- Released: 2025-09-01
- Context: 1M tokens
- Max output: 8K tokens
- Input: text, audio; output: text, audio

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $0.45 | per 1M tokens |
| Output | $1.80 | per 1M tokens |
| Cache read | $0.45 | per 1M tokens |
| Reasoning output | $1.80 | per 1M tokens |
| Audio input | $2.70 | per 1M tokens |
| Audio output | $10.80 | per 1M tokens |
| Image input | $2.70 | per 1M tokens |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:google/gemini-2.5-flash-native-audio`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Google (Gemini) | `google:google/gemini-2.5-flash-native-audio` | United States | $0.45 | $1.80 | no |

Web page: https://www.ohmygpt.com/models/google/gemini-2.5-flash-native-audio