Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior
Context
128K
128,000 tokens
Max output
32K
32,000 tokens
Input
$4.00
per 1M tokens
Output
$24.00
per 1M tokens
Providers
2
2 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by OpenAI
| Token type | Standard |
|---|---|
| Input | $4.00 |
| Output | $24.00 |
| Cache read | $0.40 |
| Audio input | $32.00 |
| Audio output | $64.00 |
Lowest input price across providers: $4.00.
Capabilities
ReasoningYes
Effort: minimal, low, medium, high, xhigh
Tool callYes
Structured outputNo
TemperatureNo
AttachmentsYes
Interleaved reasoningNo
Open weightsNo
ModeratedUnknown
Input
TextAudioImage
Output
TextAudio
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 2
2 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenAI | gpt-realtime-2.1 | 128K | 96K | 32K | $4.00 | $24.00 | — | $0.40 | — | $32.00 | $64.00 | Yes | Yes | No | No | Jul 6, 2026 |
 Vercel AI Gateway | openai/gpt-realtime-2.1 | 128K | 96K | 32K | $4.00 | $24.00 | — | $0.40 | — | $32.00 | $64.00 | Yes | Yes | Unknown | Yes | Jul 6, 2026 |