Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.
Prices for the AI credit you buy. $BINF holders pay up to 8% less.
| Charge | Price | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.080 | $0.074 | per 1M tokens |
| Outputper 1M tokens | $0.40 | $0.37 | per 1M tokens |
| Cached inputper 1M tokens | $0.0080 | $0.0074 | per 1M tokens |
| Cache writeper 1M tokens | $0.10 | $0.092 | per 1M tokens |
| Web searcheach | $0.0080 | $0.0074 | each |
The price per million tokens, by day.
Unchanged since Oct 7, 2026: $0.080 in and $0.40 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 |
|---|---|---|
| GoogleGlobal, answering | 100% | 1M |
| Claude Platform on AWS, answering | 100% | 1M |
| AzureGlobal, answering | 100% | 1M |
| Anthropic, answering | 100% | 1M |
| Amazon Bedrock, answering | 99.9% | 1M |
| GoogleEurope, answering | 100% | 1M |
| GoogleUS, answering | 99.9% | 1M |
| AzureUS, answering | 100% | 1M |
| Amazon BedrockUs east 1, answering | 100% | 1M |
| Amazon BedrockEu west 1, answering | 100% | 1M |