MiniMax: MiniMax M1 is MiniMax's model, and its measured tokenizer sits in MiniMax'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 7 other models | tk_9f84b5fb |
| API surface | No other entry shares this exact contract | api_7395250b |
| Context and output | 1,000,000 context · 40,000 max output | declared |
| Reasoning contract | Optional | declared |
| Serving providers observed | Novita, Minimax | measured 22 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: 446 prompt tokens.
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p
defaults: {"temperature":null,"top_p":null,"frequency_penalty":null}
Cite this page as the evidence record for MiniMax: MiniMax M1: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
