MiniMax M2 pricing
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,... This page tracks 4 listings in total. Highlighted lows are $0.255 per million input and $1.02 per million output (see table for which seller matches each).
Pricing across providers
Use this table to read MiniMax M2 list prices. We show 4 sources right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
FA Fireworks AI | $0.300 | $1.20 | — | — |
N Novita | $0.300 | $1.20 | $0.030 | — |
O Openrouter | $0.255 | $1.02 | — | — |
M Minimaxnative | $0.300 | $1.20 | $0.030 | — |
Input vs output · per provider
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how MiniMax M2 cost scales with traffic.
Provider
0.030000¢ / req
0.060000¢ / req
Model specifications
Quick spec sheet for MiniMax M2 before you dive back into pricing. Reported under Minimax.
- Context window
- 200,000 tokens
- Max output
- 8,192 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- No
- Released
- Oct 2025
- Primary provider
- Minimax
- Model family
- N/A
Compare MiniMax M2
Open a pair page to see MiniMax M2 next to another model with a shared provider matrix. 6 shortcuts below.
Locked
Compare with
Pick a model on both sides.
Popular MiniMax M2 comparisons
- MiniMax M2 vs GPT-4o
MiniMax M2 88% cheaper on output
- MiniMax M2 vs Claude Sonnet 4.6
MiniMax M2 92% cheaper on output
- MiniMax M2 vs Gemini 2.0 Flash
Gemini 2.0 Flash 66% cheaper on output
- MiniMax M2 vs Llama 3.1 70B
Compare pricing side by side
- MiniMax M2 vs Mistral 7B
Mistral 7B 79% cheaper on output
- MiniMax M2 vs GLM 4.7
MiniMax M2 45% cheaper on output
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: 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...
Related models
Models close to MiniMax M2 by family, provider, and context window — each with live pricing in our catalog.