MiniMax · Model identity
MiniMax M1
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...
1pricing route
What published route metadata supports
ReasoningTool use
Input modalities
Text
Supported API parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2025-06-17
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Could this workload cost less?Compare MiniMax M1 with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | minimax/minimax-m1 | $0.4 | — | $2.2 | 1M | OpenRouter API ↗ |
3 verified price changes since Aug 26, 2026
0 route availability changes recorded. No earlier prices are inferred.
Input / 1M$0.4Aug 26, 2026 → Sep 16, 2026
- Sep 16, 2026OpenRouter · Standard
Input $0.55 → $0.4
- Sep 9, 2026OpenRouter · Standard
Input $0.4 → $0.55
- Sep 8, 2026OpenRouter · Standard
Input $0.55 → $0.4