Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

  • About
  • Blog
  • Customers
  • 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

Going away November 5, 2026

minimax/minimax-m2

Model weights
Compare

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.

The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors.

Benchmarked by Artificial AnalysisOpens in new tab, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.

To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docsOpens in new tab.

Modalities
In / out price
15% off
$0.255 / $1.02per 1M
Context
205K
Released
Oct 23, 2025
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

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 (Artificial Analysis and Design Arena)
SourceBenchmarkScore
Artificial AnalysisMiniMax-M2 GPQA Diamond77.7%
Artificial AnalysisMiniMax-M2 HLE13.7%
Artificial AnalysisMiniMax-M2 IFBench72.3%
Artificial AnalysisMiniMax-M2 τ²-Bench Telecom86.8%
Artificial AnalysisMiniMax-M2 AA-LCR64.3%
Artificial AnalysisMiniMax-M2 CritPt0.9%
Artificial AnalysisMiniMax-M2 LiveCodeBench82.6%
Artificial AnalysisMiniMax-M2 Terminal-Bench Hard25.8%
Artificial AnalysisMiniMax-M2 MMLU-Pro82.0%
Artificial AnalysisMiniMax-M2 AIME 202578.3%
Design ArenaMiniMax M2 Stable Models Arena 3D Elo1095
Design ArenaMiniMax M2 Stable Models Arena Code Categories Elo1133
Design ArenaMiniMax M2 Stable Models Arena Data Visualization Elo1140
Design ArenaMiniMax M2 Stable Models Arena Game Development Elo1118
Design ArenaMiniMax M2 Stable Models Arena SVG Elo1096
Design ArenaMiniMax M2 Stable Models Arena UI Component Elo1131
Design ArenaMiniMax M2 Stable Models Arena Website Elo1141

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.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Model RankingsRanking
Latency / throughput
15% off
$0.30$0.255$1.20$1.020.79s54 tok/s
100.00%
ProviderInput / Output /M
15% offThroughputUptime
  • Favicon for Minimax
    Input $0.255 / Output $1.02
    15% off
    Throughput 54 tok/sUptime 100.00%
Throughput
54tok/s

P50, best across providers

Latency
0.79s

P50, best provider

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.
99.50%

Availability over the last 3 days

Last 72 hours
Availability 99.50%
3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability
99.65%

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 provider routing options.

1.
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.
492Mtokens
2.
Favicon for https://minara.ai/
Minara
new
167Mtokens
3.
Favicon for https://kilocode.ai/
Kilo Code
Kilo Code is an open-source AI coding agent that works across VS Code, JetBrains, and CLI to help developers ship code faster with agentic workflows.
75.2Mtokens
4.
Favicon for https://forge.local/
FORGE AI v1.0
new
59.6Mtokens
5.
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.
36.9Mtokens
Top 5 Apps
38.4M
Rest of OpenRouter
20.3M

Frequently asked questions

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency.

MiniMax M2 costs $0.255/M input tokens and $1.02/M output tokens.

MiniMax M2 has a 204,800 token context window. It supports up to 131,072 completion tokens.

Yes. MiniMax M2 accepts tools and tool_choice for function calling. It does not support response_format, so JSON output is not enforced.

MiniMax M3.1 Flash, MiniMax M3, MiniMax M2.7 and 5 more are other text models from MiniMax.

MiniMax M2 was released on October 23, 2025.