← Model list
MiniMax-M2.1
minimax·minimax/MiniMax-M2.1·Deprecated·Open weights·minimax series
Earlier MiniMax agent model for practical coding and productivity tasks
At a glance
Official price$0.30 / $1.20 per 1M
Cache read $0.03 · MiniMax (minimaxi.com)
Lowest paid$0.27 / $1.10
DevPass (LLM Gateway) Gateway · 7.8× spread
2 more $0 channels
Context204,800
⚠ Providers report 196,000–1,000,000; the table below is authoritative
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-10
Released / updated2025-12-23 / 2025-12-23
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence32.1
Value67
Coding—
Agentic—
Output speed88 tok/s
TTFT1.88 s
Value formulaIQ 32.1 ÷ min blended $0.477 = 67
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 23 providers20 with public prices · 2 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| MiniMax Token Plan (minimaxi.com) | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | ||
| MiniMax Token Plan (minimax.io) | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | ||
| DevPass (LLM Gateway) minimax-m2.1 | Gateway | $0.27 | $1.10 | — | — | 204,800 | 131,072 | |
| Meganova | Gateway | $0.28 | $1.20 | — | — | 196,608 ⚠ | 131,072 | |
| Hugging Face | Cloud | $0.30 | $1.20 | — | — | 204,800 | 131,072 | |
| Jiekou.AI minimax/minimax-m2.1 | Gateway | $0.30 | $1.20 | — | — | 204,800 | 131,072 | |
| OpenRouter minimax/minimax-m2.1 | Gateway | $0.30 | $1.20 | $0.03 | — | 204,800 | 131,072 | |
| Amazon Bedrock minimax.minimax-m2.1 | Cloud | $0.30 | $1.20 | — | — | 204,800 | 131,072 | |
| Merge Gateway minimax/minimax-m2.1 | Gateway | $0.30 | $1.20 | $0.03 | $0.375 | 204,800 | 8,192 | |
| ZenMux minimax/minimax-m2.1 | Gateway | $0.30 | $1.20 | $0.03 | $0.38 | 204,000 ⚠ | 64,000 | |
| MiniMax (minimaxi.com)Official | First-party | $0.30 | $1.20 | $0.03 | $0.375 | 204,800 | 131,072 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1OpenRouter$87.60
2Merge Gateway$87.60
3ZenMux$87.60
4Ofox$87.60
5MiniMax (minimaxi.com) · Official$87.60
6Vercel AI Gateway$87.60
2 more channels offer $0 (MiniMax Token Plan (minimaxi.com), MiniMax Token Plan (minimax.io)); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to OpenRouter to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark2 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 74 | resolved | Source ↗ |
| SWE-Bench Pro | dataset: public | 36.81 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = loweffort = mediumeffort = higheffort = xhigheffort = maxbudget_tokens ≥ 1,024 ≤ 131,071Toggle (on / off)
17 / 23 providers expose no reasoning control (reasoning_options: []).
Related models
MiniMax H3same series—MiniMaxAI/MiniMax-M2.5same series$0.30 / $1.20MiniMax-M3same series$0.30 / $1.20DeepSeek V4 Flashcheaper alternative$0.14 / $0.28GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0MiMo-V2.5cheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended