Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

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

Company

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

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

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

MiniMax: MiniMax M2.5

minimax/minimax-m2.5

Model weights
Compare

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

Modalities

In / Out Price

$0.225 / $0.90per 1M

Context

205K

Released

Feb 12, 2026

Compare

About MiniMax: MiniMax M2.5

OpenRouter makes MiniMax: MiniMax M2.5 available through a unified, OpenAI-compatible API using the model ID minimax/minimax-m2.5. Requests can be routed across 8 providers, including DigitalOcean, Venice, StreamLake, AtlasCloud, NovitaAI, MiniMax Highspeed, SiliconFlow and Friendli, with automatic failover when an endpoint is unavailable.

MiniMax: MiniMax M2.5 accepts text and returns text. It has a 204,800-token context window.

On OpenRouter, MiniMax: MiniMax M2.5 costs $0.225/M input tokens and $0.90/M output tokens, with separate rates for Cache Read at $0.06/M tokens. Effective pricing can be lower when prompt caching applies. It was released on February 12, 2026.

More models from MiniMax

  • H3
  • Speech 2.8 HD
  • Speech 2.8 Turbo

Frequently asked questions

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working...

MiniMax M2.5 costs $0.225/M input tokens and $0.90/M output tokens, with separate rates for Cache Read at $0.06/M tokens.

MiniMax M2.5 has a 204,800 token context window.

Yes. MiniMax M2.5 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

MiniMax M2.5 is served by 8 providers on OpenRouter: DigitalOcean, Venice, StreamLake, AtlasCloud, NovitaAI, MiniMax Highspeed, SiliconFlow and Friendli. 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 M2.5 was released on February 12, 2026.