OpenAIGPT-4oAug 15, 2025

OpenAI: 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
128K
tokens
Max Output
16K
tokens
Released
Aug 15, 2025
Arena Rank
Output Speed
92
tokens/sec
Time to First Token
420ms
TTFT

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Logit Bias
Adjust token weights
Log Probs
Token probabilities
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
structured_outputs
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
top_logprobs
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouter$2.50$10.00

Benchmarks

Artificial Analysis
Intelligence IndexArtificial Analysis
54.4/100
Coding IndexArtificial Analysis
42.8/100
Math IndexArtificial Analysis
60.8/100
MMLU-PROArtificial Analysis
0.724/1
GPQA DiamondArtificial Analysis
0.538/1
MATH-500Artificial Analysis
0.763/1
AIME 2024Artificial Analysis
0.097/1
Humanity's Last ExamArtificial Analysis
0.013/1
LiveCodeBenchArtificial Analysis
0.395/1
SciCodeArtificial Analysis
0.158/1

Model IDs

OpenRouteropenai/gpt-4o-audio-preview

Tags

tool-calling
Compare with another model

Related Models