Anthropic: Claude 3 Haiku is Anthropic's model. Its measured tokenizer sits with the Claude group, which is evidence that it builds on the Claude tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Anthropic's authorship of the model itself.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 1 other model | tk_2d06485c |
| API surface | No other entry shares this exact contract | api_b5cd1a4d |
| Context and output | 200,000 context · 4,096 max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | Amazon Bedrock | measured 21 August 2026 |
Click a row to open the full comparison.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 7 prompt tokens.
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) #multimodal
Cite this page as the evidence record for Anthropic: Claude 3 Haiku: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
