Key Info
Requesty now serves GPT-6.2 Astra and GPT-6.2 Sol through its API gateway, with published per-token pricing for both models.
Highlights
- Astra pricing: $8 per 1M input tokens, $0.40 per 1M cached input tokens, $40 per 1M output tokens.
- Astra is 20% cheaper than GPT-6 Astra on input, and cached input is 60% cheaper.
- Sol retains GPT-6.1 Sol rates: $2 input, $0.10 cached input, $10 output per 1M tokens.
- Model IDs for API calls are gpt-6.2-astra and gpt-6.2-sol.