MiniMax-01
MiniMax · released Jan 12, 2025 · MiniMaxAI/MiniMax-Text-01
- Type
- Open weights
- Params
- 456B
- Context
- 1M
about 750K words of context
Our take
Written Aug 2, 2026MiniMax-01 is a 456.1-billion-parameter text-and-image model with a one-million-token request limit, released in early 2025. Its weights can be downloaded, though the licence terms are undisclosed, and no benchmark scores are available to verify its quality.
Choose this when you need downloadable weights and the longest context window available — over one million tokens — for long-document work or video-frame analysis. It is a budget-conscious option for such tasks. Skip it if you need verified quality scores, if you require a known licence for commercial use, or if you need reliable throughput across multiple providers.
The case for it
- Extremely long context window among downloadable models: 1,000,192 tokens.
- Open weights at moderate per-token pricing, with 456.1 billion parameters available for local deployment.
The case against it
- No measured quality or performance data in our catalogue: zero benchmark scores, no chat Elo, no reasoning or coding scores.
- Throughput data is thin and partially unverified: only 29 tokens per second on one provider, unverified on the other.
- Licence terms are undisclosed, so commercial use, redistribution and modification rights are unverified.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up MiniMax-01 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
GeForce RTX 4090 · 24 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Apple M1 Pro (16-core GPU) · 32 GB
Too large for this card. The weights do not fit even with part of them offloaded to system memory.
Comfortable fit
Apple M3 Ultra (80-core GPU) · 512 GB
Room to spare. 85.9 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.20 in / $1.10 out
- Context served
- 1M
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.20 / $1.10 | 1M | not measured | Unknown | Unknown | Unknown |
| Minimax | $0.20 / $1.10 | 1M | 27 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✗ | ✗ |
| Minimax | ✗ | ✗ | ✗ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 0 of 2 listings say yes, 2 say no.
When we formed this view
Dates behind this page
Prices last checked 3d ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model yet.
Identifiers
- Hugging Face
- MiniMaxAI/MiniMax-Text-01
- Architecture
- Mixture of experts
- Modality record
- text+image->text
- Catalogue slug
- minimax-minimax-01