Pricing
What one request costs
Prompt24Ktokens
Cached prefix17Ktokens
Reply2Ktokens
per request to GPT-5.6 Sol
- Prompt
- 44%
- Cached
- 10.3%
- Reply
- 45.8%
GPT-5.6 Sol: $0.03276 per request
24,000 prompt tokens, 16,800 of them cached, and 1,500 reply tokens.
The same request, across other models
