Claude Haiku 4.5
AnthropicProprietaryNon-reasoningProvisionalReleased Oct 15, 2025Input: text, image, file
Overall score
41.1
Rank 135 of 222 · 31.4–50.9
Context window
200K
200,000 tokens
Price per 1M tokens
$1.00 in · $5.00 out
✓ Verified on Anthropic's pricing page
Blended price
$2.00
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
Benchmark results (6)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| MazeBench | 0 | #20 of 42 |
| JobBench | 16.0 | #30 of 34 |
Coding
| SWE-bench Verified | 73.3 | #49 of 98 |
| VulcanBench v3 | 76.2 | #13 of 14 |
Multimodal
| Design Arena Website | 1122 | #78 of 91 |
| ParseBench | 45.17 | #33 of 37 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| ✓ Official (Anthropic) checked Oct 17, 2026 · Claude Haiku 4.5 | $1.00 | $5.00 | $0.10 |
| BenchLM list price | $1.00 | $5.00 | $0.10 |
| OpenRouter anthropic/claude-haiku-4.5 | $1.00 | $5.00 | $0.10 |
Anthropic official public pricing for Claude Haiku 4.5 as referenced by Anthropic's April 2026 model pages.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| WebDev (coding)(20251001) | 1330 | #123 · 29.1K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Similar score
- Muse Glimmer 30B41.2 · $0.53
- DeepSeek-R141.1 · $0.96
- MiMo-V2-Flash41.0 · —
- Grok 3 [Beta]41.0 · —
- DeepSeek V3.140.8 · $0.42