Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $6.00 | $5.52 | per 1M tokens |
| Outputper 1M tokens | $30.00 | $27.60 | per 1M tokens |
| Cached inputper 1M tokens | $0.60 | $0.55 | per 1M tokens |
| Cache writeper 1M tokens | $7.50 | $6.90 | per 1M tokens |
| Web searcheach | $0.012 | $0.011 | each |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $6.00 in and $30.00 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| Claude Platform on AWS, answering | 96.9% | 1M |
| AzureGlobal, answering | 74.5% | 1M |
| GoogleGlobal, answering | 99.6% | 1M |
| Amazon Bedrock, answering | 99.6% | 1M |
| Anthropic, answering | 99.2% | 1M |
| GoogleEurope, answering | 100% | 1M |