MiniMax M2
minimax/minimax-m2Efficient open reasoning tuned for agent loops, low price, interleaved thinking, dependable tools.
Model overview
Context window
200K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
Yes
self-hostable
Capabilities
5
of 11 tags
Description
MiniMax M2 is a reasoning model from MiniMax. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. MiniMax’s stated focus is multimodal breadth: text, video, speech. Its mean it can also be self-hosted under its licence.
Capabilities
- Reasoning
- Spends extra billed tokens thinking before it answers, trading latency and cost for accuracy.
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- JSON mode
- Constrains the response to valid JSON matching a schema you supply.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Open weights
- The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.
Strengths & weaknesses
Strengths
- Cheapest credible reasoning model
- Agent-oriented design
- Open weights
Weaknesses
- Newer model with a shorter track record
- Peak reasoning trails R1
Pricing
| Rate | Price | Unit |
|---|---|---|
| Input | — quoted on request | — |
| Output | — quoted on request | — |
This model is not provisioned yet; the rate is quoted on request.
Context window
200Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Supported |
| Reasoning | Supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Not supported |
Example use cases
Agent orchestration
Budget reasoning
Tool-heavy workflows
Comparison
Compare against anything →| Attribute | MiniMax M2 | DeepSeek R1 | GLM-4.6 |
|---|---|---|---|
| Context window | 200K | 164K | 200K |
| Input price | R0.00 | R0.00 | R0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Not supported | Supported |
| Vision input | Not supported | Not supported | Not supported |
| Open weights | Supported | Supported | Supported |
| Prompt caching | Not supported | Not supported | Supported |
Best value in each row is highlighted. Blank cells are facts the supplier does not publish, not zeroes.
Provider information
View MiniMax →MiniMax · 稀宇科技 · Shanghai, China · est. 2021
MiniMax builds across more modalities than almost any peer, million-token text models, the Hailuo video line, and production-grade speech synthesis. Its M-series brought efficient open reasoning to the mix, rounding out one of the most complete catalogues in the ecosystem.
Recent releases
Documentation
Frequently asked questions
Input is billed at R0.00 per 1M tokens, and there is no separate output charge. Every figure on this page is an illustrative placeholder.
Yes. MiniMax M2's parameters are published, so it can be downloaded, inspected, fine-tuned and self-hosted under its licence. Self-hosting trades per-token pricing for infrastructure you run.
Prompt and response share one window: MiniMax M2 accepts up to 200K tokens in total, so a long input leaves less room for the answer. The median across reasoning models is 200K. Recall is strongest well inside the limit. Test at your real prompt depth before relying on the ceiling.
DeepSeek R1 is the closest neighbour in the catalogue, with 164K of context at R0.00 per 1M tokens in. Put both in a comparison before wiring a fallback chain, so the trade-off is a decision rather than a default.