Skip to content
  • Models
  • Rankings
  • Ori
Sign Up
Sign Up
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for minimax

MiniMax: MiniMax M2.7

minimax/minimax-m2.7

Model weights
Compare

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.

Trained for production-grade performance, M2.7 handles workflows such as live debugging, root cause analysis, financial modeling, and full document generation across Word, Excel, and PowerPoint. It delivers strong results on benchmarks including 56.2% on SWE-Pro and 57.0% on Terminal Bench 2, while achieving a 1495 ELO on GDPval-AA, setting a new standard for multi-agent systems operating in real-world digital workflows.

Modalities

In / Out Price

30% off

$0.21 / $0.84per 1M

Context

205K

Released

Mar 18, 2026

Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), Floor (cheapest), or Exacto (highest tool-calling accuracy).

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for MiniMax: MiniMax M2.7 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisMiniMax-M2.7 Intelligence Index22.8
Artificial AnalysisMiniMax-M2.7 Coding Index52.6
Artificial AnalysisMiniMax-M2.7 Agentic Index15.3
Artificial AnalysisMiniMax-M2.7 GPQA Diamond87.4%
Artificial AnalysisMiniMax-M2.7 HLE29.6%
Artificial AnalysisMiniMax-M2.7 IFBench75.7%
Artificial AnalysisMiniMax-M2.7 τ²-Bench Telecom84.8%
Artificial AnalysisMiniMax-M2.7 AA-LCR78.3%
Artificial AnalysisMiniMax-M2.7 GDPval-AA24.9%
Artificial AnalysisMiniMax-M2.7 CritPt0.6%
Artificial AnalysisMiniMax-M2.7 SciCode50.1%
Artificial AnalysisMiniMax-M2.7 Terminal-Bench Hard39.4%
Artificial AnalysisMiniMax-M2.7 AA-Omniscience Accuracy26.8%
Artificial AnalysisMiniMax-M2.7 AA-Omniscience Non-Hallucination Rate64.4%
Design ArenaMiniMax M2.7 Models Arena 3D Elo1219
Design ArenaMiniMax M2.7 Models Arena Asciiart Elo1157
Design ArenaMiniMax M2.7 Models Arena Code Categories Elo1242
Design ArenaMiniMax M2.7 Models Arena Data Visualization Elo1245
Design ArenaMiniMax M2.7 Models Arena Game Development Elo1223
Design ArenaMiniMax M2.7 Models Arena SVG Elo1148
Design ArenaMiniMax M2.7 Models Arena UI Component Elo1222
Design ArenaMiniMax M2.7 Models Arena Website Elo1251

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Explore more models

AI Model RankingsRanking
30% off
$0.30$0.21$1.20$0.84$0.06$0.0421.55s40 tps
99.96%
60% off
$0.60$0.24$2.40$0.96$0.06$0.0247.99s95 tps
78.67%
10% off
$0.30$0.27$1.20$1.08$0.06$0.0541.18s47 tps
99.85%
$0.30$1.20$0.0601.23s13 tps
99.74%
$0.30$1.20$0.0601.48s52 tps
100.00%
$0.38$1.70$0.0704.80s26 tps
73.98%
$0.60$1.80--0.47s232 tps
91.90%
$0.60$2.40$0.0604.81s45 tps
97.67%
$0.60$2.40$0.0601.46s37 tps
98.66%

Throughput

232tok/s

P50, best across providers

Latency

0.47s

P50, best provider

AutoExacto Benchmarks
GPQA DiamondTAU-BenchDeepInfra Turbo81.2%--Groq89.6%69.7%MiniMax Highspeed85.2%74.0%MARA78.5%--AtlasCloud85.7%69.3%MiniMax84.5%69.3%DeepInfra72.5%67.3%
+3 more providers
Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

98.54%

Availability over the last 3 days

Last 72 hours
Availability 98.54%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
98.41%
Without Routing
89.42%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.

1.
Favicon for https://stan.store/
Sahasra
All-in-one creator store
91.1Btokens
2.
Favicon for https://openclaw.ai/
OpenClaw
OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.
20.9Btokens
3.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
20.5Btokens
4.
Favicon for https://pi.dev/
pi
There are many coding agents, but this one is yours.
18.4Btokens
5.
Favicon for https://claude.ai/apple-touch-icon.png
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
4.25Btokens

Frequently asked questions

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent collaboration, enabling it to plan, execute, and refine complex tasks across dynamic environments.

MiniMax M2.7 costs $0.21/M input tokens and $0.84/M output tokens, with separate rates for Cache Read at $0.042/M tokens.

MiniMax M2.7 has a 204,800 token context window.

Yes. MiniMax M2.7 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

MiniMax M2.7 is served by 8 providers on OpenRouter: GMICloud, MARA, NovitaAI, AtlasCloud, MiniMax Highspeed, DeepInfra Turbo, Groq, and SambaNova. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

MiniMax M2.7 was released on March 18, 2026.