OpenAI: GPT-4o Audio
GPT-4o Audio is a specialised multimodal model supporting audio input and output, but its benchmark scores are weak across reasoning, coding, and math — it serves a niche use case and is not competitive with current-generation text models for general business tasks.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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.
Capabilities
Architecture
| Modality | Text + Audio → Text + Audio |
| Tokenizer | GPT |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $2.50 | $0.002500 |
| Output | $10.00 | $0.010000 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
