Why high: an exact fingerprint shared with 8 models.
MiniMax: MiniMax M2 is MiniMax's model, and its measured tokenizer sits in MiniMax's own signature group alongside its sibling models. Measured models from Undisclosed (stealth) carry the same vocabulary, which reads as reuse of MiniMax's tokenizer line and questions nobody's authorship; they are listed under "Shares this fingerprint" below.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 8 other models | tk_9f84b5fb |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_3e795d93 |
| How much it can read and write | Reads up to 204,800 tokens at once, writes up to 176,947 | its own listing |
| Whether it thinks before answering | Always reasons, and cannot be turned off | its own listing |
| Who served our requests | Minimax | we measured it, 21 August 2026 |
Click a row to open the full comparison.
We sent MiniMax: MiniMax M2 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: 39 prompt tokens.
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
Supported parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
defaults: {"temperature":1,"top_p":0.95,"frequency_penalty":null}
