Claude Haiku 4.5 vs GPT-5 mini
Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.
Claude Haiku 4.5
Anthropic · Oct 2025
Anthropic's fast tier: Sonnet-4-class coding performance at $1/$5 and more than twice the speed.
GPT-5 mini
OpenAI · Aug 2025
A fast, cheap distillation of GPT-5 for high-volume workloads — one fifth of the flagship's price with most of its everyday capability.
The verdict
Claude Haiku 4.5 and GPT-5 mini split the 2 benchmarks they share evenly (1–1), so capability alone won't settle this one. GPT-5 mini is about 2.9x cheaper per blended million tokens (3:1 input:output mix). GPT-5 mini also takes 400K of context versus 200K for Claude Haiku 4.5.
Benchmark head-to-head 1–1
Specs & pricing
| Claude Haiku 4.5 | GPT-5 mini | |
|---|---|---|
| modhub Index | — | — |
| Input price / 1M | $1 | $0.25 |
| Output price / 1M | $5 | $2 |
| Context window | 200K | 400K |
| Max output | 64K | 128K |
| Open weights | no | no |
| Reasoning model | yes | yes |
| Multimodal input | text, image | text, image |
| Knowledge cutoff | Feb 2025 | May 2024 |
| Released | Oct 2025 | Aug 2025 |
| Example monthly cost* | $17.50 | $5.50 |
* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.
Frequently asked questions
- Which is better, Claude Haiku 4.5 or GPT-5 mini?
- Claude Haiku 4.5 and GPT-5 mini split the 2 benchmarks they share evenly (1–1), so capability alone won't settle this one. GPT-5 mini is about 2.9x cheaper per blended million tokens (3:1 input:output mix). GPT-5 mini also takes 400K of context versus 200K for Claude Haiku 4.5.
- Which is cheaper, Claude Haiku 4.5 or GPT-5 mini?
- Claude Haiku 4.5 costs $1/$5 per million input/output tokens, while GPT-5 mini costs $0.25/$2. For a typical workload of 10M input and 1.5M output tokens per month, that's $17.50 versus $5.50.
- Which model is better for coding, Claude Haiku 4.5 or GPT-5 mini?
- On SWE-bench Verified — the standard agentic-coding benchmark — Claude Haiku 4.5 scores 73.3% versus ~71% for GPT-5 mini, making Claude Haiku 4.5 the stronger pick for coding agents.
More comparisons
Claude Haiku 4.5 vs GPT-5.5GPT-5 mini vs GPT-5.5Claude Haiku 4.5 vs GPT-5.2GPT-5 mini vs GPT-5.2Claude Haiku 4.5 vs GPT-5.1GPT-5 mini vs GPT-5.1Claude Haiku 4.5 vs GPT-5GPT-5 mini vs GPT-5Claude Haiku 4.5 vs OpenAI o3GPT-5 mini vs OpenAI o3Claude Haiku 4.5 vs Claude Fable 5GPT-5 mini vs Claude Fable 5