Claude Haiku 4.5 vs GPT-5 Mini
Compare Claude Haiku 4.5 and GPT-5 Mini on the metrics that decide an agent workload.
| Metric | Claude Haiku 4.5 | GPT-5 Mini |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Input / 1M | $1.00 | $0.25 |
| Output / 1M | $5.00 | $2.00 |
| Cache read / 1M | $0.10 (−90%) | $0.03 (−90%) |
| Reuse-adj @55% | $1.63 | $0.59 |
| Context | 200K | 400K |
| Cache capture | 90% | 85% |
| Warm TTFT | 110ms (−66%) | 150ms (−63%) |
| Quality index | 80 | 82 |
Teal marks the better value in each row. Reuse-adjusted assumes 55% prefix reuse and a 25% output share.
Pick Claude Haiku 4.5 when it answers faster on warm cache hits, it captures more of the available reuse.
Pick GPT-5 Mini when it scores higher on the composite quality index, it is cheaper once prefix reuse is priced in, it carries the larger 400K context window.
GPT-5 Mini wins on both reuse-adjusted cost and quality here, so it is the default pick. Reach for Claude Haiku 4.5 only when a specific constraint (modality, latency floor, or licensing) forces it.
Claude Haiku 4.5 vs GPT-5 Mini, answered.
Is Claude Haiku 4.5 or GPT-5 Mini cheaper?
At 55% prefix reuse, Claude Haiku 4.5 blends to about $1.63 per 1M tokens and GPT-5 Mini to about $0.59. GPT-5 Mini is cheaper on that basis.
Which has the larger context window?
GPT-5 Mini has the larger window: 400K vs 200K tokens.
Which captures more reuse?
Claude Haiku 4.5 shows higher measured cache capture (90% vs 85%) in the Zumik corpus.
Let an alias pick for you.
Route to whichever model wins under current policy automatically. Zumik resolves the alias to the best fit per request, so you never hard-code a loser.