Skip to main content

​
MiniMax (Reasoning & Code)

POST https://api.minimaxi.chat/v1/chat/completions
Uses SSE streaming with OpenAI-compatible tool-calling format. Supports reasoning content. Best for: Reasoning-heavy workloads, code generation, agentic workflows.
MiniMax is a solid Chinese provider, but DeepSeek and MiMo remain cheaper and more capable for most workloads. Consider MiniMax if you want provider diversity or have specific needs its model lineup serves well.

​
Getting an API Key

  1. Go to platform.minimaxi.chat
  2. Sign up or log in
  3. Navigate to API Keys and create a new key
  4. Paste it into Wolffish → Settings → Models → MiniMax

​
Models

ModelContextModesInput / Output (per MTok)Notes
MiniMax-M31MOff, On0.30/0.30 / 1.20Latest flagship. Strong reasoning. Cached: $0.06/MTok.
MiniMax-M2.7200KOn0.30/0.30 / 1.20Previous gen flagship. Cached: $0.06/MTok.
MiniMax-M2.7-highspeed200KOn0.60/0.60 / 2.40Faster inference, 2× price. Cached: $0.06/MTok.
MiniMax-M2.5200KOn0.30/0.30 / 1.20Code-optimized. Cached: $0.03/MTok.
MiniMax-M2.5-highspeed200KOn0.60/0.60 / 2.40Code-optimized, faster. Cached: $0.03/MTok.
MiniMax-M2.1200KOn0.30/0.30 / 1.20Reasoning. Cached: $0.03/MTok.
MiniMax-M2.1-highspeed200KOn0.60/0.60 / 2.40Reasoning, faster. Cached: $0.03/MTok.
MiniMax-M2200KOn0.30/0.30 / 1.20Base model. Cached: $0.03/MTok.

​
Reasoning modes

The brain icon next to the message box controls how this model reasons. Click it to cycle through the modes the selected model supports. Two separate ideas combine here:

​
Thinking — whether the model reasons

  • Off — the model answers immediately. Fastest and cheapest; ideal for simple, direct tasks.
  • On — the model first works through the problem in a dedicated reasoning pass before replying. Slower and uses more tokens, but markedly more accurate on multi-step, logical, or ambiguous tasks.

​
Effort — how hard it thinks

Only effort-capable models expose this; it applies once thinking is on.
  • High — standard reasoning depth. The right default for most agentic work.
  • Max — the model reasons longer and deeper for the hardest problems. More tokens and latency in exchange for higher quality on complex work.

​
Button states

StateColourMeaning
OffgrayThinking off — direct answer
OnblueThinking on — no effort control
HighpurpleThinking on, standard effort
MaxorangeThinking on, maximum effort
Each model shows only the states it genuinely supports. If a model always reasons (can’t be turned off) or has no effort control, the button reflects that and locks where there’s nothing to change. Wolffish remembers your choice per model. On MiniMax: MiniMax-M3 is On / Off. The M2.x models reason always-on, so the button is locked on.