| API |
|---|
| GPT-6 Astra Input | $10.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6 Astra Cached input | $1.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6 Astra Output | $50.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6.1 Sol Input | $2.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6.1 Sol Cached input | $0.10 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6.1 Sol Output | $10.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6.1 Terra Input | $1.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6.1 Terra Cache read | $0.05 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6.1 Terra Output | $5.00 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6 Luna Input | $0.10 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6 Luna Cached input | $0.01 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-6 Luna Output | $0.50 |
per 1M tokens | per use |
Standard · Pricing above reflects standard processing rates for context lengths under 272K. |
| GPT-Image-2.5 Sunburst Image inputs | $8.00 |
per 1M tokens | per use |
Image: · for inputs |
| GPT-Image-2.5 Sunburst Image cached inputs | $2.00 |
per 1M tokens | per use |
Image: · for cached inputs |
| GPT-Image-2.5 Sunburst Image outputs | $30.00 |
per 1M tokens | per use |
Image: · for outputs |
| GPT-Image-2.5 Sunburst Text inputs | $5.00 |
per 1M tokens | per use |
Text: · for inputs |
| GPT-Image-2.5 Sunburst Text cached inputs | $1.25 |
per 1M tokens | per use |
Text: · for cached inputs |
| GPT-Image-2.5 Flare Image inputs | $8.00 |
per 1M tokens | per use |
Image: · for inputs |
| GPT-Image-2.5 Flare Image cached inputs | $2.00 |
per 1M tokens | per use |
Image: · for cached inputs |
| GPT-Image-2.5 Flare Image outputs | $30.00 |
per 1M tokens | per use |
Image: · for outputs |
| GPT-Image-2.5 Flare Text inputs | $5.00 |
per 1M tokens | per use |
Text: · for inputs |
| GPT-Image-2.5 Flare Text cached inputs | $1.25 |
per 1M tokens | per use |
Text: · for cached inputs |
| GPT-Live-1 per minute | $0.05 |
per minute | per use |
— |
| GPT-Live-1 per second | $0.00083 |
per second | per use |
— |
| GPT-Realtime-2.1 Audio inputs | $32.00 |
per 1M tokens | per use |
Audio: · for inputs |
| GPT-Realtime-2.1 Audio cached inputs | $0.40 |
per 1M tokens | per use |
Audio: · for cached inputs |
| GPT-Realtime-2.1 Audio outputs | $64.00 |
per 1M tokens | per use |
Audio: · for outputs |
| GPT-Realtime-2.1 Text inputs | $4.00 |
per 1M tokens | per use |
Text: · for inputs |
| GPT-Realtime-2.1 Text cached inputs | $0.40 |
per 1M tokens | per use |
Text: · for cached inputs |
| GPT-Realtime-2.1 Text outputs | $24.00 |
per 1M tokens | per use |
Text: · for outputs |
| GPT-Realtime-2.1 Image inputs | $5.00 |
per 1M tokens | per use |
Image: · for inputs |
| GPT-Realtime-2.1 Image cached inputs | $0.50 |
per 1M tokens | per use |
Image: · for cached inputs |
| GPT-Realtime-2.1 mini Audio inputs | $10.00 |
per 1M tokens | per use |
Audio: · for inputs |
| GPT-Realtime-2.1 mini Audio cached inputs | $0.30 |
per 1M tokens | per use |
Audio: · for cached inputs |
| GPT-Realtime-2.1 mini Audio outputs | $20.00 |
per 1M tokens | per use |
Audio: · for outputs |
| GPT-Realtime-2.1 mini Text inputs | $0.60 |
per 1M tokens | per use |
Text: · for inputs |
| GPT-Realtime-2.1 mini Text cached inputs | $0.06 |
per 1M tokens | per use |
Text: · for cached inputs |
| GPT-Realtime-2.1 mini Text outputs | $2.40 |
per 1M tokens | per use |
Text: · for outputs |
| GPT-Realtime-2.1 mini Image inputs | $0.80 |
per 1M tokens | per use |
Image: · for inputs |
| GPT-Realtime-2.1 mini Image cached inputs | $0.08 |
per 1M tokens | per use |
Image: · for cached inputs |
| GPT-Live-Transcribe per minute | $0.017 |
per minute | per use |
— |
| GPT-Live-Transcribe per second | $0.00028 |
per second | per use |
— |
| GPT-Transcribe per minute | $0.0045 |
per minute | per use |
— |
| GPT-Transcribe per second | $0.00008 |
per second | per use |
— |
| GPT-Realtime-Translate per minute | $0.034 |
per minute | per use |
— |
| GPT-Realtime-Translate per second | $0.00057 |
per second | per use |
— |
| Web search calls | $10.00 |
per 1k calls | per use |
Search content tokens are free. |
| Containers 1 GB container | $0.03 |
per container | per use |
Now: · 1 GB |
| Containers 64GB container | $1.92 |
per container | per use |
Now: · 64GB |
| Containers 1 GB container session | $0.03 |
per 20-minute session per container | per use |
Starting March 31, 2026: · 1 GB |
| Containers 64GB container session | $1.92 |
per 20-minute session per container | per use |
Starting March 31, 2026: · 64GB |