GPT-Realtime mini
Summary
GPT-Realtime mini is a proprietary language model from OpenAI, released on 6 Oct 2025. It accepts text and audio and generates text and audio, with a 32K-token context window and up to 4K output tokens per response. As of 21 Oct 2026, the lowest listed API price is $0.60 per million input tokens and $2.40 per million output tokens (Vercel AI Gateway), across 1 provider we track.
Cost-efficient realtime speech-to-speech model for voice agents
Last verified 21 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | OpenAI |
|---|---|
| Release date | 6 Oct 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 32K (32,000 tokens) [models.dev] |
| Max output | 4K tokens [models.dev] |
| Knowledge cutoff | 1 Oct 2023 [models.dev] |
| Input | Text and audio [models.dev] |
| Output | Text and audio [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
GPT-Realtime mini API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Vercel AI Gateway openai/gpt-realtime-mini | $0.60 | $2.40 | $0.06 | 32K | models.dev, 21 Oct 2026 |
Frequently asked questions
What is the context window of GPT-Realtime mini?
GPT-Realtime mini has a context window of 32,000 tokens (32K) and can generate up to 4,096 tokens in a single response, according to models.dev.
How much does the GPT-Realtime mini API cost?
GPT-Realtime mini is listed from $0.60 per million input tokens and $2.40 per million output tokens (Vercel AI Gateway). Prices last verified 21 Oct 2026.
Is GPT-Realtime mini open source?
No. GPT-Realtime mini is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.
When was GPT-Realtime mini released?
OpenAI released GPT-Realtime mini on 6 Oct 2025, according to models.dev.
Change history
- Context window changed from none to 32K
- Max output changed from none to 4K
- Tool calling changed from no to yes
- Added to the directory
- Now listed on Vercel AI Gateway