AI Desk · AI FingerprintingNew arrival
Why moderate: near-exact agreement (48 of 48 strings) with meta-llama/llama-3.2-3b-instruct, short of a full exact signature.
Pareto 26.9 is Unbiased's model. Its measured tokenizer sits with the Llama3 group, which is evidence that it builds on the Llama3 tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Unbiased's authorship of the model itself.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counted, using the 48 strings that came back reliably | we measured it |
| How its API is set up | Set up identically to 2 other listings, field for field | api_7c06b7a0 |
| How much it can read and write | Reads up to 262,144 tokens at once, writes up to 131,072 | its own listing |
| Who served our requests | Unbiased | we measured it, 17 October 2026 |
Click a row to open the full comparison.
We sent Pareto 26.9 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.
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 24 prompt tokens.
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
Supported parameters
max_tokensresponse_formattemperaturetool_choicetoolstop_p
