Claude 3 Haiku pricing & benchmarks
Claude 3 Haiku is available from Anthropic at $0.250 per million input tokens and $1.25 per million output tokens ($0.500 blended at 3:1). It accepts up to 200,000 tokens of context. Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) …
Pricing
Per million tokens · OpenRouter
Input$0.250
Output$1.25
Blended (3:1)$0.500
Specification
anthropic/claude-3-haiku
Context window200K
Max output4K
ReleasedMar 2024
LicenceProprietary
Modalitiesin:text, in:image, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 36.3% ±2.4 | — | 2025-01-27 | Independently run · Epoch AI |
| OTIS Mock AIME | 1.8% ±0.8 | — | 2025-02-25 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| Mistral Small 3 | Mistral AI | $0.058 (−89%) | 45.3% | Compare → |
| gpt-oss-120b | OpenAI | $0.070 (−86%) | 75.8% | Compare → |
| Phi 4 | Microsoft | $0.088 (−83%) | 56.1% | Compare → |
| DeepSeek V4 Flash 0731 | DeepSeek | $0.113 (−78%) | 91.0% | Compare → |
| GPT-5 Nano | OpenAI | $0.138 (−73%) | 69.4% | Compare → |
Compare Claude 3 Haiku
FAQ
How much does Claude 3 Haiku cost?
Claude 3 Haiku costs $0.250 per million input tokens and $1.25 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.500 per million tokens.
What is Claude 3 Haiku's context window?
Claude 3 Haiku accepts up to 200,000 tokens of context, and can generate up to 4,096 output tokens.
How good is Claude 3 Haiku on benchmarks?
Claude 3 Haiku scores 36.3% on GPQA Diamond, independently run and published by Epoch AI. 2 benchmark results are listed on this page, each with its run date and source.
Is there a cheaper model as good as Claude 3 Haiku?
Yes — 5 models in our catalogue cost less per token than Claude 3 Haiku and score at least as high on the same benchmark. The cheapest is Mistral Small 3 at $0.058 per million tokens blended.