Comparison · prices as of 2026-07-04
Claude Haiku 4.5 vs GPT-5.1
On price alone, Claude Haiku 4.5 (Anthropic) runs about 40% cheaper than GPT-5.1 for a typical chat workload (2K input + 500 output tokens, 1,000 requests/day). Whether that's the right trade depends on the capability gap — pricing below, verify quality on your own evals.
| Spec | Claude Haiku 4.5 | GPT-5.1 |
|---|---|---|
| Input / MTok | $1 | $1.25 |
| Output / MTok | $5 | $10 |
| Context window | 200K | 400K |
| Max output | 64K | 128K |
| Class | fast | frontier |
| Reference workload / month | $135.00 | $225.00 |
Sources: Anthropic pricing · OpenAI pricing. Run your own numbers in the cost calculator.