Claude 3.5 Haiku
Fast + cheap with a huge context — great for RAG and classification.
At a glance
- Context window
- 200k tokens
- Max output
- 8k tokens
- Input price
- $0.80 / 1M tokens
- Output price
- $4.00 / 1M tokens
- Time to first token
- 0.5s
- Input modalities
- text
- Output modalities
- text
- License
- Proprietary
- Provider
- Anthropic
Benchmark scores
Public scores from each provider; bars compare this model against the leader in each benchmark.
- 200k context cheap
- Fast
- Reliable on extraction
- Weaker reasoning than Sonnet
- RAG
- Classification
- Form filling
Models you should also evaluate
Anthropic’s 2026 flagship — best-in-class on code and long-horizon agents.
The Anthropic sweet spot — Opus-class coding at a fraction of the price.
The model that made coding agents viable — still a top pick.
More from Anthropic
Anthropic’s 2026 flagship — best-in-class on code and long-horizon agents.
The Anthropic sweet spot — Opus-class coding at a fraction of the price.
The model that made coding agents viable — still a top pick.
Claude 3.5 Haiku vs… popular head-to-heads
One-click matchups against the models people compare Claude 3.5 Haiku with most.
Claude 3.5 Haiku — frequently asked questions
Need help choosing between models?
Compare every option in one sortable table — intelligence, speed and price on a single page.