MiniMax M2
MiniMaxReleased Oct 27, 2025Open weights · Modified MITminimax-m2
- Reasoning
- yes
- Knowledge cutoff
- January 2026
- Context
- 197K tokens
- Max output
- 128k tokens
- Input
- text
- API features
- tools, structured outputs, JSON mode, seed, logprobs
- MiniMax's API
- yes, as MiniMax-M2
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from MiniMax · cutoff: aiknowledgecutoff.com
Run it yourself
open weights, Modified MIT · fits 1 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 230B
- 10B active per token (MoE)
- Memory needed
- 138 GB
- in INT4 · 276 GB in INT8
- Smallest cloud setup
- 2× H100
- 160 GB · $4.30/h, about $3,139 a month
- Worth it above
- 2B tokens
- a month, against the cheapest API at $1.27 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 138 GB | 2× H100 · $4.30/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 276 GB | 4× H100 · $8.60/h | near-lossless |
| FP16 (full) | 552 GB | 8× H100 · $17.20/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (256 GB unified), about $9,499 once, or $0.3615/h over 3 years, electricity aside; it pays for itself after about 7B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| Novita AIprecision not stated · 200K ctx · 128K out | $0.30 | $1.20 | $0.03 | — | — | — | Oct 8 |
| Minimaxfp8 · 200K ctx · 128K out−15% | $0.26 | $1.02 | — | 25 | 0.74 s | 100% | Oct 23 |
| Googleprecision not stated · 192K ctx | $0.30 | $1.20 | — | — | — | 13.3% | Oct 22 |
3 of 3 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · −N%: a discount off the host's list price · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| Minimax | fp8 | 200K | 128K | yes | no | yes |
| not stated by the host | 192K | not stated by the host | yes | yes | yes | |
| Novita AI | not stated by the host | 200K | 128K | — | — | — |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
MiniMax M2 spec sheet, field by field, with sources
MiniMax M2 spec sheetmaker-declared
What MiniMax declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- 196,608 tokens
- Parameters
- 228,689,764,864≈ 228.7B
- Active experts
- 8 of 256 active per token
- Weight precision
- fp8
- License
- Modified MIT — open weights, conditionalcurated · read 2026-09-07Scope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- not published by the maker≈ January 2026 third-party estimate — not the maker's figurecurated
- Modalities
- text
- Max output (official)
- to verify
- Release date
- to verify≈ October 27, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- MiniMaxM2ForCausalLM
- Layers
- 62
- Vocabulary
- 200,064 tokens
- Weights first published
- October 22, 2025
- Weights last updated
- December 23, 2025
- Papers
- arXiv:2504.07164 · arXiv:2509.06501 · arXiv:2509.13160
MiniMaxAI/MiniMax-M2 · config.json @ 757303d · read 2026-10-08 · 6 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| Minimax | $0.76 | $2.55 | $2.04 |
| $0.90 | $3.00 | $2.40 | |
| Novita AI | $0.90 | $3.00 | $2.40 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other MiniMax models · all its models, hosts and history ›
- MiniMax-M312 providers · from $1.19
- MiniMax M2.59 providers · from $1.22
- MiniMax M2.77 providers · from $1.05
- MiniMax M3.1 Flash4 providers · from $0.60
- MiniMax M12 providers · from $2.60
- MiniMax M2.12 providers · from $1.50