Claude Haiku 4.5 vs GPT-5 nano
GPT-5 nano costs 93% less at typical usage ($0.14 vs $2.00 per 1M tokens). Claude Haiku 4.5 scores higher on 11 of 11 tasks.
| Spec | Claude Haiku 4.5 | GPT-5 nano |
|---|---|---|
| Input /1M | $1.00 | $0.05 |
| Output /1M | $5.00 | $0.40 |
| Typical /1M | $2.00 | $0.14 |
| Context window | 200k | 400k |
| Speed | Blazing | Blazing |
| Privacy | Strong | Standard |
| Open weights | No | No |
Claude Haiku 4.5
Steady since we started tracking (Jul 13, 2026)
GPT-5 nano
Steady since we started tracking (Jul 13, 2026)
Quality by task
Coding88/72
Agents87/68
Reasoning84/74
Writing85/76
Chat88/80
Classify86/82
Extract86/80
Summarize87/80
Translate84/80
Vision84/78
General86/76
Price your own prompt against both
The free estimator ranks Claude Haiku 4.5, GPT-5 nano and every other catalog model by cost and quality for your exact workload.
Open the estimatorGet notified when either model's price changes
We watch the catalog for list-price changes. Opt in with just an email, no account, and unsubscribe in one click anytime.
Also compare Claude Haiku 4.5
Also compare GPT-5 nano
Prices are list $/1M tokens, hand-maintained from public provider pricing. Task scores are benchmark-informed 0-100 estimates, not gospel — validate on your own evals before moving production traffic. Not affiliated with any model provider.