AI Rate CardGPT-Realtime-2 vs GPT-Realtime Mini: API price and specs
GPT-Realtime-2 is 68% cheaper than GPT-Realtime Mini on input price.
GPT-Realtime-2 is 4% cheaper than GPT-Realtime Mini on output price.
GPT-Realtime-2 is 50% cheaper than GPT-Realtime Mini on a 1M-in / 200k-out workload.
GPT-Realtime-2 has a 300% larger context than GPT-Realtime Mini.
| Field | GPT-Realtime-2 | GPT-Realtime Mini |
|---|---|---|
| Lowest input, per 1M | $3.20 | $10.00 +212.5% |
| Median input, per 1M | $32.00 +220% | $10.00 |
| Lowest output, per 1M | $19.20 | $20.00 +4.2% |
| Median output, per 1M | $64.00 +220% | $20.00 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $7.04 | $14.00 +98.9% |
| Context | 128K | 32K +75% |
| Max output | 32K | 4K +87.2% |
| Providers | 3 | 3 |
| Regions | — | — |
| Accepts | audio, image, text | audio, image, text |
| Returns | audio, text | audio, text |
| Type | Speech to speech | Speech to speech |
| Free option | no | no |
| Cheapest provider | cometapi | fastrouter |
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-Realtime-2 or GPT-Realtime Mini?
GPT-Realtime-2 is 68% cheaper than GPT-Realtime Mini on input price. GPT-Realtime-2 is 4% cheaper than GPT-Realtime Mini on output price. GPT-Realtime-2 is 50% cheaper than GPT-Realtime Mini on a 1M-in / 200k-out workload.
Which has the larger context, GPT-Realtime-2 or GPT-Realtime Mini?
GPT-Realtime-2: 128K tokens; GPT-Realtime Mini: 32K tokens.
Where can I use both GPT-Realtime-2 and GPT-Realtime Mini?
openai, vercel