GPT Realtime Whisper
GPT Realtime Whisper is OpenAI's language model with a 16K context window and up to 2K output tokens. A streaming speech-to-text model optimized for low-latency transcript delivery from live audio, tailored for real-time applications requiring fine-tuned transcription control.
Capabilities
Input2/5
Text✓
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| GPT-5.5 | 1.1M | $5.00 | $30.00 | Available | |
| GPT-5.4 Mini | 1.1M | $0.750 | $4.50 | Available | |
| GPT-5.4 Nano | 1.1M | $0.200 | $1.25 | Available | |
| GPT-5.4 | 1.1M | $2.50 | $15.00 | Available | |
| GPT-5.3 Codex | 400K | $1.75 | $14.00 | Available | |
| GPT-5.2 Codex | 400K | $1.75 | $14.00 | Available | |
| GPT-5.2 | 410K | $1.75 | $14.00 | Available | |
| GPT-5.1 | 410K | $1.25 | $10.00 | Available | |
| GPT-5.1 Codex | 400K | $1.25 | $10.00 | Available | |
| GPT-5.1 Codex Mini | 400K | $0.250 | $2.00 | Available | |
| GPT Realtime Whisper | — | 16K | — | — | Current |