MiniMax-M2.1 vs MiniMax-M2 Her
MiniMax-M2.1 comes out ahead, 48 to 45 on our weighted score.
- Our pick
MiniMaxMiniMax-M2.1
48/100- ECI—
- Price$0.30 / $1.20
- Context205K
- MiniMax
MiniMax-M2 Her
45/100- ECI—
- Price$0.30 / $1.20
- Context66K
Add a model
Make it a three-way comparison.
MiniMax-M2.1 is our pick
MiniMax-M2.1 is the better all-round choice, scoring 48/100 against MiniMax-M2 Her (45). It leads on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceSame priceMiniMax-M2.1 $0.525 · MiniMax-M2 Her $0.525 per 1M tokens (3:1 blend)
- Longest contextMiniMax-M2.1MiniMax-M2.1 204,800 · MiniMax-M2 Her 65,536 tokens
- Widest inputsSame inputsMiniMax-M2.1: Text · MiniMax-M2 Her: Text
- Self-hostingMiniMax-M2.1Publishes downloadable weights
| Measure | Weight | MiniMax-M2.1 | MiniMax-M2 Her |
|---|---|---|---|
| Price | 50% | 63 | 63 |
| Inputs & features | 30% | 35 | 35 |
| Context window | 20% | 32 | 12 |
| Overall | 100% | 48/100 | 45/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | MiniMax-M2.1MiniMax | MiniMax-M2 HerMiniMax |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | $0.30 | $0.30 |
| Output | $1.20 | $1.20 |
| Cached input | $0.03 | — |
| Blended (3:1) | $0.525 | $0.525 |
| Long-context rate | Same rate | Same rate |
| Price source | Official MiniMax (minimax.io) API | Median of 4 providers |
| Limits | ||
| Context window | 204,800 tokens (best) | 65,536 tokens |
| Max output | 131,072 tokens (best) | 2,048 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | Open | Proprietary |
| API model ID | MiniMax-M2.1 | — |
| API providers | 13 (best) | 4 |
| Released | Dec 23, 2025 | Jan 23, 2026 |
| Knowledge cutoff | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- MiniMax-M2.1$5.40
- MiniMax-M2 Her$5.40
Which should you choose?
Which is better: MiniMax-M2.1 or MiniMax-M2 Her?
MiniMax-M2.1 is the better all-round choice, scoring 48/100 against MiniMax-M2 Her (45). It leads on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, MiniMax-M2.1 or MiniMax-M2 Her?
MiniMax-M2.1 and MiniMax-M2 Her cost the same: $0.30 input / $1.20 output per million tokens.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. MiniMax-M2.1 has not been scored yet and MiniMax-M2 Her has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for MiniMax-M2.1 and MiniMax-M2 Her yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.
Which has the bigger context window?
MiniMax-M2.1 has the largest context window at 204,800 tokens, against 65,536 for MiniMax-M2 Her. Maximum output per response: MiniMax-M2.1 up to 131,072, MiniMax-M2 Her up to 2,048 tokens.
Which can read images, PDFs, audio or video?
MiniMax-M2.1 accepts text; MiniMax-M2 Her accepts text. They handle the same number of input types.
Are any of these open source?
MiniMax-M2.1 publishes its weights and can be self-hosted; MiniMax-M2 Her is proprietary.
Which is newer?
MiniMax-M2 Her is the newest, released Jan 23, 2026. MiniMax-M2.1 came out Dec 23, 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
