AI Desk · AI FingerprintingNew arrival
Why high: an exact fingerprint shared with 1 model that declares the same family, without a second signal of a different kind yet.
Anthropic: Claude Haiku 5.5 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.
Measured on 8 October 2026, the day after it was listed. Claude Haiku 5.5 counts tokens exactly as Claude Sonnet 5.5 does on all 50 strings, and as Claude Opus 5.5, Opus 5 and Fable 5.1 do on the 49 they return (Anthropic's input filter stops the base64 string on those three before the model runs). It agrees with Claude Haiku 4.5 on 15 of the 50: Claude's newer vocabulary, the one Anthropic introduced with Opus 4.7, now runs from Haiku to Fable.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 1 other model | tk_310f7ba9 |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_151f6909 |
| How much it can read and write | Reads up to 1,000,000 tokens at once, writes up to 128,000 | its own listing |
| Whether it thinks before answering | Reasons when asked to, at max, xhigh, high, medium, low, medium by default | its own listing |
| Who served our requests | Claude Platform on AWS | we measured it, 8 October 2026 |
Click a row to open the full comparison.
We sent Anthropic: Claude Haiku 5.5 fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
Overhead subtracted: 8 prompt tokens.
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity
defaults: {}
