AI Rate CardGPT-3.5-turbo vs GPT-Audio Mini: API price and specs
GPT-3.5-turbo is 58% cheaper than GPT-Audio Mini on input price.
GPT-3.5-turbo is 69% cheaper than GPT-Audio Mini on output price.
GPT-3.5-turbo is 63% cheaper than GPT-Audio Mini on a 1M-in / 200k-out workload.
GPT-Audio Mini has a 681.2% larger context than GPT-3.5-turbo.
| Field | GPT-3.5-turbo | GPT-Audio Mini |
|---|---|---|
| Lowest input, per 1M | $0.25 | $0.60 +140% |
| Median input, per 1M | $0.50 | $0.60 +20% |
| Lowest output, per 1M | $0.75 | $2.40 +220% |
| Median output, per 1M | $1.50 | $2.40 +60% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.40 | $1.08 +170% |
| Context | 16K +87.2% | 128K |
| Max output | 4K +75% | 16K |
| Providers | 12 | 4 +66.7% |
| Regions | US | — |
| Accepts | image, pdf, text | audio, pdf, text |
| Returns | text | audio, text |
| Type | Text models | Text models |
| Free option | no | no |
| Cheapest provider | openrouter | abacus |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
Frequently asked questions
Which is cheaper, GPT-3.5-turbo or GPT-Audio Mini?
GPT-3.5-turbo is 58% cheaper than GPT-Audio Mini on input price. GPT-3.5-turbo is 69% cheaper than GPT-Audio Mini on output price. GPT-3.5-turbo is 63% cheaper than GPT-Audio Mini on a 1M-in / 200k-out workload.
Which has the larger context, GPT-3.5-turbo or GPT-Audio Mini?
GPT-3.5-turbo: 16K tokens; GPT-Audio Mini: 128K tokens.
Where can I use both GPT-3.5-turbo and GPT-Audio Mini?
kilo, openai, openrouter