← Model list
MiniMax-M2.7
minimax·minimax/MiniMax-M2.7·GA·Open weights·minimax series
Open MiniMax flagship for coding agents, office automation, and complex environments
At a glance
Official price$0.30 / $1.20 per 1M
Cache read $0.06 · MiniMax (minimaxi.com)
Lowest paid$0.08 / $0.32
DevPass (LLM Gateway) Gateway · 10.2× spread
5 more $0 channels
Context204,800
⚠ Providers report 192,000–262,100; the table below is authoritative
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-01
Released / updated2026-03-18 / 2026-03-18
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence38.9
Value278
Coding52.6
Agentic25.9
Output speed61 tok/s
TTFT1.75 s
Cost per task$0.0777
Value formulaIQ 38.9 ÷ min blended $0.140 = 278
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 42 providers36 with public prices · 2 free · 3 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia minimaxai/minimax-m2.7 | First-party | Free | — | — | 204,800 | 131,072 | ||
| MiniMax Token Plan (minimaxi.com) | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | ||
| UnoRouter minimax-m2.7:free | Gateway | Free | — | — | 204,800 | 131,072 | ||
| MiniMax Token Plan (minimax.io) | Gateway | Subscription | $0 | $0 | 204,800 | 131,072 | ||
| SCNet Token Plan | Gateway | Subscription | $0 | — | 204,800 | 131,072 | ||
| DevPass (LLM Gateway) minimax-m2.7 | Gateway | $0.08 | $0.32 | $0.017 | $0.375 | 204,800 | 131,072 | |
| EmpirioLabs AI minimax-m2-7 | Gateway | $0.15 | $0.60 | $0.03 | — | 200,000 ⚠ | 32,768 | |
| Deep Infra | Cloud | $0.25 | $1.00 | $0.05 | — | 196,608 ⚠ | 131,072 | |
| Requesty minimax-m2.7 | Gateway | $0.27 | $1.08 | $0.054 | $1.08 | 200,000 ⚠ | 128,000 | |
| Pioneer | Gateway | $0.279 | $1.20 | $0.279 | $0.279 | 204,800 | 131,000 | |
| MiniMax (minimaxi.com)Official | First-party | $0.30 | $1.20 | $0.06 | $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
1DevPass (LLM Gateway)$24.44
2EmpirioLabs AI$45.60
3Deep Infra$76.00
4Requesty$82.08
5OrcaRouter$91.20
6Hugging Face$91.20
15MiniMax (minimaxi.com) · Official$91.20
5 more channels offer $0 (Nvidia, MiniMax Token Plan (minimaxi.com), UnoRouter etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to DevPass (LLM Gateway) to save $66.76/mo (73%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark3 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | harness: Claude Code | 79.9 | resolved | Source ↗ |
| SWE-Bench Pro | harness: Claude Code | 56.2 | resolve rate | Source ↗ |
| Terminal-Bench | v2.1 | 51.1 | success 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 = maxeffort = nonebudget_tokensToggle (on / off)
32 / 42 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