MiniMax M1
MiniMaxReleased Jun 17, 2025Open weights · Apache 2.0minimax-m1
- Reasoning
- yes
- Knowledge cutoff
- January 2026
- Context
- 9.8M tokens
- Max output
- 40k tokens
- Input
- text
- API features
- tools, seed
- MiniMax's API
- yes, as MiniMax-M1
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from MiniMax · cutoff: aiknowledgecutoff.com
The cheapest host, Minimax, serves a 1M context (maker: 9.77M). Weights and context per host
Run it yourself
open weights, Apache 2.0 · too large for the 6 workstations in our guideSelf-host guide ›- Parameters
- 456B
- 45.9B active per token (MoE)
- Memory needed
- 274 GB
- in INT4 · 547 GB in INT8
- Smallest cloud setup
- 4× H100
- 320 GB · $8.60/h, about $6,278 a month
- Worth it above
- 2B tokens
- a month, against the cheapest API at $2.60 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 274 GB | 4× H100 · $8.60/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 547 GB | 8× H100 · $17.20/h | near-lossless |
| FP16 (full) | 1094 GB | multi-node, over 640 GB | reference quality |
At home: 274 GB in INT4 is beyond any desktop or Mac in our machines table, so it means a multi-GPU server.
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 |
|---|---|---|---|---|---|---|---|
| Minimax1M ctx (9.77M) · 40K out | $0.40 | $2.20 | — | 75 | 0.92 s | 100% | Oct 23 |
| Novita AIbf16 · 1M ctx (9.77M) · 40K out | $0.55 | $2.20 | — | — | — | — | Oct 23 |
2 of 2 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 · 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 | not checked yet | 1M | 40K | no | no | yes |
| Novita AI | bf16 | 1M | 40K | yes | no | yes |
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 M1 spec sheet, field by field, with sources
MiniMax M1 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
- 10,240,000 tokens
- Parameters
- 456,089,655,296≈ 456.1B
- Active experts
- 2 of 32 active per token
- Weight precision
- BF16
- License
- Apache 2.0 — open weights, permissivecurated · 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≈ June 17, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
Also declared in the weights
- Architecture class
- MiniMaxM1ForCausalLM
- Layers
- 80
- Vocabulary
- 200,064 tokens
- Weights first published
- June 5, 2025
- Weights last updated
- July 7, 2025
- Paper
- arXiv:2506.13585
MiniMaxAI/MiniMax-M1-40k · config.json @ 2d1d1c2 · 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 | $1.50 | $4.30 | $3.80 |
| Novita AI | $1.65 | $5.50 | $4.40 |
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 M23 providers · from $1.27
- MiniMax M2.12 providers · from $1.50