MoonshotAI: Kimi K2.7 Code is Moonshot AI's model, and its measured tokenizer sits in Moonshot AI's own signature group alongside its sibling models. No other maker's measured model shares it so far.
| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Exact match with 2 other models | tk_ea6068bf |
| API surface | No other entry shares this exact contract | api_82054774 |
| Context and output | 262,144 context · 235,929 max output | declared |
| Reasoning contract | Mandatory | declared |
| Serving providers observed | SiliconFlow | measured 3 September 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: 8 prompt tokens.
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_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 MoonshotAI: Kimi K2.7 Code: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
