GPT-Realtime-1.5: API pricing, providers and specs
GPT-Realtime-1.5 is a audio model by OpenAI. 3 providers serve it, from $12.80 to $16 /1M; the lowest price is at CometAPI.
A newer version is out: GPT-Realtime-2.1 · released Jul 9, 2026
How GPT-Realtime-1.5 compares
Against the 43 audio models on the site priced the same way.
- Pricey for its class: at $12.80 /1M, its lowest price is above 77% of comparable models (median $6.15).
- Its 32K-token context window is larger than 30% of them (median 128K), about 50 pages of text.
- 3 providers serve it; 59% of comparable models have fewer.
GPT-Realtime-1.5 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 CometAPI | $3.20/1M | $12.80/1M | — | — |
| Vercel AI Gateway | $4/1M | $16/1M | $0.40/1M | — |
 FastRouter | $4/1M | $16/1M | $0.40/1M | 32K |
- CometAPI$12.80
- Vercel AI Gateway$16
- FastRouter$16
Specs
- Type
- Audio
- Maker
- OpenAI
- Inputs
- Text, Audio
- Outputs
- Text, Audio
- Context
- 32K≈ 50 pages of text
- Max output
- 4K
- Capabilities
- Prompt caching, Tool calling
- Released
- Feb 23, 2026
- License
- —
- Open weights
- —
Alternatives to GPT-Realtime-1.5
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| GPT-Realtime-1.5this model | $12.80/1M | 32K | — | 3 |
 Gemini 3.8 Flash TTS | $6.30/1M | 8K | — | 8 |
| Gemini 3.8 Live | $4.50/1M | 131K | — | 3 |
| Gemini 3.1 Flash TTS Preview | $14/1M | 8K | — | 10 |
 Qwen Audio 3.0 Realtime Plus | $6.40/1M | — | — | 1 |
| Qwen Audio 3.1 Realtime Plus | $5.98/1M | 256K | — | 3 |
| Qwen3-Omni Flash | $6/1M | — | — | 2 |
| Gemini 2.5 Flash Lite Preview TTS | $10/1M | — | — | 1 |
| Gemini 2.5 Flash TTS | $10/1M | 8K | — | 4 |
More from OpenAI
GPT-Realtime-1.5 FAQ
The lowest price for GPT-Realtime-1.5 is $12.80 /1M, at CometAPI.
CometAPI, at $12.80 /1M. 3 providers serve GPT-Realtime-1.5; the table above lists every one with its price.
GPT-Realtime-1.5 reads up to 32K tokens per request and writes up to 4K.
We have not found GPT-Realtime-1.5's weights published by its maker.
3 API providers serve GPT-Realtime-1.5. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us