OpenAI First-PartyVerified 2026-11-12
GPT-6.1 Sol API Pricing & Cost Rules
API Model ID: gpt-6.1-sol · Context Window: 1,050,000 tokens (Max Input: 922,000) · Max Output: 128,000 tokens
Context Tiers & Token Rate Card (USD per 1M Tokens)
| Tier | Std Input | Std Output | Cache Read | Write (Short) | Write (Long) |
|---|---|---|---|---|---|
| Standard (<= 272K) | $2.00 | $10.00 | $0.1 | $2.5 | $5.00 |
| Long Context (> 272K) | $4.00 | $15.00 | $0.2 | $5.00 | $10.00 |
Prompt Caching Rules
Supported: Yes (automatic)
Minimum Cacheable Prefix: 1,024 tokens
Hourly Cache Storage: $0
Read = 0.05x (95% off = $0.10/1M short, $0.20/1M long). Write total rate = 1.25x (30m) or 2.50x (12h). Min 1,024 visible input tokens.
Batch API & Hosting Notes
Batch Supported: Yes (50% discount · 24h)
Caching in Batch: Allowed + Batch discount stacks onto cache reads
50% off all columns including 95%-discounted cached reads ($0.05/1M short) and cache writes.
Regional data residency & FedRAMP endpoints add +10% uplift. Fast tier = 2x, Ultrafast = 6x.