// MiniMax
MiniMax-M2.1
A MiniMax model. 1 prices across 1 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- ¥2.1 / ¥8.4
- Lowest (official)
- ¥2.1 / ¥8.4
- Context
- 205K
- AA index
- 20.9
Prices checked 2026-10-19Official sources linked on every rowNo estimates
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | MiniMax |
|---|---|
| Context window | 205K (204,800 tokens) |
| Max output | 131K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · modified-mit (custom) · Hugging Face |
| Parameters | 229B (from weight files) |
| Released | Dec 23, 2025 (OpenRouter listing date) |
| Model IDs | MiniMax-M2.1 |
02Prices on 1 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| Official Vendor’s China site, billed in CNY | Official 10-19 | ¥2.1 | ¥8.4 | ¥0.21 | 0.549 | 205K | Priority tier 1.5x; Not listed on the pay-as-you-go pricing page since 2026-10-20 (last seen 2026-10-19 at this price) |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Vendor’s China site, billed in CNY
Official - Self-host the open weights
GPU / VRAM sizing and build plans→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexMiniMax-M2.1
- 20.9
- Output speed (median)
- 72 tok/s
- Time to first token
- 1.55s
- AA index per $ (blended)
- 38.19
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| MMLU-Pro | 88.0% | vendor | 2026-03-11 |
| Terminal-Bench 2.0 | 36.6% | official | 2025-12-23 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
No price change recorded since we started tracking (2026-10-10).
06More from MiniMax
FAQ
How much does the MiniMax-M2.1 API cost?
On the official pricing page: ¥2.1 / ¥8.4 per 1M input / output tokens, cached input ¥0.21 (checked 2026-10-19).
What is the context window of MiniMax-M2.1?
205K tokens of context, up to 131K output tokens. Platforms may cap it lower – see the table.
Is MiniMax-M2.1 open source?
Yes, the weights are published on Hugging Face (MiniMaxAI/MiniMax-M2.1). Licence: modified-mit (custom).