Claude Haiku 5.5 pricing table
| Item | Value |
|---|---|
| Input | $0.10 |
| Cached input | $0.0100 |
| Cache write (5 min) | $0.125 |
| Output | $0.50 |
| Context | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Long context | above 100,000 tokens: 5× input and 5× output |
The same usage on other models
Monthly cost of 1,000 requests a day, with 2,000 input and 500 output tokens each:
| Model | Input | Output | Example per month |
|---|---|---|---|
| Claude Haiku 5.5 | $0.10 | $0.50 | $13.50 |
| GPT-6 Luna | $0.10 | $0.50 | $13.50 |
| GPT-5.6 Luna | $0.20 | $1.20 | $30.00 |
| Claude Haiku 4.5 | $1.00 | $5.00 | $135.00 |
| Claude Sonnet 5.5 | $2.00 | $10.00 | $270.00 |
| GPT-6.1 Sol | $2.00 | $10.00 | $270.00 |
| GPT-6 Sol | $2.00 | $10.00 | $270.00 |
| GPT-5.6 Terra | $2.00 | $12.00 | $300.00 |
| Claude Opus 5.5 | $4.00 | $20.00 | $540.00 |
| GPT-5.6 Sol | $4.00 | $20.00 | $540.00 |
| Claude Fable 5.1 | $10.00 | $50.00 | $1,350 |
| GPT-6 Astra | $10.00 | $50.00 | $1,350 |
How to pay less
Use prompt caching for the fixed part of your calls and the Batch API (50% off) for anything that can wait up to 24 hours. The calculator above shows the effect of each.