Kwaipilot: KAT-Coder-Air V2.5 is Kwaipilot's model. Its measured tokenizer sits with the Qwen group, which is evidence that it builds on the Qwen tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Kwaipilot's authorship of the model itself.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 1 other model | tk_06ffa14a |
| API surface | Identical contract to 1 other entry | api_0df9ca8e |
| Context and output | 256,000 context · 80,000 max output | declared |
| Reasoning contract | None declared | declared |
| Serving providers observed | StreamLake | 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: 10 prompt tokens.
KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
Supported parameters
logprobsmax_tokenspresence_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for Kwaipilot: KAT-Coder-Air V2.5: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.
