Openai
0.00%Context—
Max output—
p50 latency—
Throughput—
Input price$0.0002
Output price$0
No training
Model directory
Baseer model profileTranscription model
openai/gpt-realtime-whisper
gpt-realtime-whisper
GPT Realtime Whisper is a streaming speech-to-text model for applications that need low-latency transcript deltas from live audio. It is designed for realtime use cases where developers need to tune latency and accuracy. GPT Realtime Whisper is priced by audio duration rather than text tokens.
Input / 1M tokens$0.0002
Output / 1M tokens$0
Maximum context—
Inference providers1
Price comparison
USD per one million tokens, using current provider data.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Openai | — | — | — | — | 0.000% | $0.0002 | $0 |
What can this model do?
Available modalities and capabilities across inference providers.
AudioTextRealtime connectionRealtime transcription
Technical profile
- Model type
- Transcription model
- Release date
- May 7, 2026
- Knowledge cutoff
- —
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- —
Model identifier
openai/gpt-realtime-whisperModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.