GPT-4o Audio
The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input and $80 per million output audio tokens.
Context window
This model accepts 128K tokens in one request (~96K words of text).
What fits in one request
- FitsShort documentAbout 1,500 words of text
- FitsLong documentAbout 37K words of text
- Won't fitSmall codebaseAbout 150K words of text
- Won't fitFull novelAbout 375K words of text
Specifications
Context size, pricing, and release info in one place.
- Context window
- 128,000 tokens (128K)
- Max output tokens
- 16,384 tokens (16K)
- Speed tier
- balanced
- Provider
- Openai
- Model family
- GPT-4o
- Release date
- Aug 2025
- Input cost
- $2.50/M / 1M tokens
- Output cost
- $10.00/M / 1M tokens
Capabilities
See which features this model supports, such as vision, tools, and streaming.
- Tool use
- Can call external tools and APIs
- Supported
- Function calling
- Structured function call interface
- Supported
- Streaming
- Returns tokens as they are generated
- Supported
- Batch API
- Process many requests asynchronously
- Supported
- Vision
- Accepts image inputs alongside text
- Not supported
- Extended thinking
- Shows its chain-of-thought reasoning
- Not supported
- Web search
- Can browse the web during a request
- Not supported
- Prompt caching
- Reuse repeated prompt prefixes cheaply
- Not supported
Best for
Jump to a guide or ranking that matches each workload.
Compare GPT-4o Audio
Open a side-by-side comparison with one click.
- GPT-4o Audio vs Amazon Titan Text Express
GPT-4o Audio has 204% larger context window
- GPT-4o Audio vs Amazon Titan Text Lite
GPT-4o Audio has 204% larger context window
- GPT-4o Audio vs Amazon Titan Text Premier
GPT-4o Audio has 204% larger context window
- GPT-4o Audio vs Claude Instant
GPT-4o Audio has 28% larger context window
- GPT-4o Audio vs Anthropic Claude
GPT-4o Audio has 28% larger context window
- GPT-4o Audio vs Codellama 34b Instruct
GPT-4o Audio has 3025% larger context window
Frequently asked questions
Short answers about context size and how this model behaves.
More from Openai
Other models by Openai in our catalog.
Powered by Mem0
Use a smaller model.
Get better results.
Mem0 gives your AI long-term memory so you stop re-sending context on every call. That means you can use a smaller, faster, cheaper model — and still get better answers.
Example: a multi-turn chat session
80% less to send — works with any model