GPT-Audio
Summary
GPT-Audio is a proprietary language model from OpenAI, released on 28 Aug 2025. It accepts text and audio and generates text and audio, with a 128K-token context window and up to 16K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $2.50 per million input tokens and $10 per million output tokens (OpenRouter), across 1 provider we track.
Speech generation model for controllable voice, narration, and audio delivery
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | OpenAI |
|---|---|
| Release date | 28 Aug 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 128K (128,000 tokens) [models.dev] |
| Max output | 16K tokens [models.dev] |
| Knowledge cutoff | 1 Oct 2023 [models.dev] |
| Input | Text and audio [models.dev] |
| Output | Text and audio [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
GPT-Audio API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter openai/gpt-audio | $2.50 | $10 | – | 128K | OpenRouter, 18 Nov 2026 |
Frequently asked questions
What is the context window of GPT-Audio?
GPT-Audio has a context window of 128,000 tokens (128K) and can generate up to 16,384 tokens in a single response, according to models.dev.
How much does the GPT-Audio API cost?
GPT-Audio is listed from $2.50 per million input tokens and $10 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is GPT-Audio open source?
No. GPT-Audio is a proprietary model; OpenAI has not released its weights. It is available through APIs including OpenRouter.
When was GPT-Audio released?
OpenAI released GPT-Audio on 28 Aug 2025, according to models.dev.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Gemini 2.5 Computer Use Preview 10-2025 | Google DeepMind | 7 Oct 2025 | 128K | $1.25 | $10 | Closed |
| Sonar Pro Search | Perplexity | 30 Oct 2025 | 200K | $3 | $15 | – |
| Pixtral Large (25.02) | Mistral AI | 8 Apr 2025 | 128K | $2 | $6 | Closed |
| Nano Banana Pro Preview | Google DeepMind | 20 Nov 2025 | 66K | $2 | $12 | Closed |
| Claude Haiku 4.5 | Anthropic | 15 Oct 2025 | 200K | $1 | $5 | Closed |
| Claude Opus 4.5 | Anthropic | 24 Nov 2025 | 200K | $5 | $25 | Closed |
Change history
- Name changed from GPT Audio to GPT-Audio
- Release date changed from 19 Jan 2026 to 28 Aug 2025
- Knowledge cutoff changed from none to 1 Oct 2023
- Open weights changed from none to no