HASTATAgent stack guide gpt
GPT-Realtime-2.1
Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context128K
Output32K
Providers2
CapabilitiesTool calling, Reasoning, Image input
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 OpenAIgpt-realtime-2.1 | $4.00 | $24.00 | $0.40 | 128K | 2026-07-06 |
 Vercel AI Gatewayopenai/gpt-realtime-2.1 | $4.00 | $24.00 | $0.40 | 128K | 2026-07-06 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text, audio, image → text, audio