The Orchestrator › Models › OpenAI
OpenAI: gpt-realtime-2.1
GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows.
Specifications
| Provider | OpenAI |
| Model ID | openai/gpt-realtime-2.1 |
| Context window | 128K tokens (128,000) |
| Modalities | text + audio → text + audio |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2026-07-09 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | openai/gpt-realtime-2.1 | $4.00 | $24.00 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $4.00 | $24.00 | 128K |
Capabilities
Audio inputControllable reasoningNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, reasoning, include_reasoning