minimax

MiniMax: MiniMax M2.5 (free)

by minimax New

OpenRouter
Tools Reasoning Long Context

About

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.

Specifications

Context Length 197K
Max Output Tokens 197K
Modality text->text
Input text
Output text
Supported Parameters include_reasoning, max_tokens, reasoning, response_format, seed, stop, temperature, tools
Content Moderation Yes

Error Rate

Based on feedback reported by Free LLM Router users. Error rate reflects the percentage of requests that encountered issues such as rate limiting, unavailability, or errors. Learn more.

Loading chart...

Availability

Available 5 of 5 tracked days. Daily snapshots show whether this model was accessible as a free model on OpenRouter.

FebMar
ModelDays181920212223242526272812345678910111213141516171819
MiniMax: MiniMax M2.5 (free)5

Similar Models

nvidia NVIDIA: Nemotron Nano 9B V2 (free) 128K arcee-ai Arcee AI: Trinity Mini (free) 131K nvidia NVIDIA: Nemotron 3 Nano 30B A3B (free) 256K nvidia NVIDIA: Nemotron 3 Super (free) 262K openai OpenAI: gpt-oss-20b (free) 131K

Frequently Asked Questions

Is MiniMax: MiniMax M2.5 (free) free to use?

Yes, MiniMax: MiniMax M2.5 (free) is completely free to use through OpenRouter. You can access it via the Free LLM Router API at no cost.

What is the context window for MiniMax: MiniMax M2.5 (free)?

MiniMax: MiniMax M2.5 (free) supports a context window of 197K tokens (196,608 tokens).

What is the maximum output length for MiniMax: MiniMax M2.5 (free)?

MiniMax: MiniMax M2.5 (free) can generate up to 197K tokens (196,608 tokens) per response.

Does MiniMax: MiniMax M2.5 (free) support function calling (tools)?

Yes, MiniMax: MiniMax M2.5 (free) supports function calling / tool use, enabling it to interact with external APIs and services.

Does MiniMax: MiniMax M2.5 (free) support reasoning?

Yes, MiniMax: MiniMax M2.5 (free) supports reasoning capabilities, allowing it to show its step-by-step thought process.