GPT Audio
by OpenAI · openai/gpt-audio · #268 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:41 AM UTC · refreshed hourly
The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$2.50
per 1M tokens
Output
$10.00
per 1M tokens
Blended (3:1)
$4.38
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT Audio (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $4.38 | $0.265 | — |
| 50% | $4.38 | $0.265 | −0% |
| 90% | $4.38 | $0.265 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00425 | $4.25 |
| Document summary | 8,000 | 1,000 | $0.03 | $30.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.095 | $95.00 |
| Long-context analysis | 150,000 | 5,000 | $0.425 | $425.00 |
Specs
Context window
128K
tokens
Max output
16K
tokens
Input modalities
text, audio
Tokenizer
GPT