LLM Perks

MiniMax M2.5

Free right now Frontier
ReasoningCodingTool useOpen weights

MiniMax M2.5 is a language model from MiniMax. It is currently free at 1 provider with up to 205K tokens of context. The model supports step-by-step reasoning, is suited to coding, supports tool calling. Its weights are open, so it can also run locally.

Developer
MiniMax
Context
205K tokens
Type
Text
License
Open weights
Free since
September 20, 2026

Where to use MiniMax M2.5 for free

Each row is a separate free endpoint with its own limits.

ProviderContextLimitCard
UnoRouter
minimax-m2.5:free
205K No-card free models use shared capacity and per-model limits; availability can change. No Open

Quick start

curl https://api.unorouter.com/v1/chat/completions \
  -H "Authorization: Bearer $UNOROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m2.5:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Example for UnoRouter. Any OpenAI-compatible client works: Cursor, Cline, OpenCode, Open WebUI.

Benchmarks

Intelligence Index
22.8
GPQA Diamond
84.8%
Humanity's Last Exam
20.5%
Terminal-Bench Hard
34.8%
τ²-Bench
95.3%
Long context (LCR)
73.3%

Source: Artificial Analysis · MiniMax-M2.5

Similar free models

FAQ

Is MiniMax M2.5 free?

Yes. As of November 2, 2026, MiniMax M2.5 is free at UnoRouter. Each provider has its own limits — see the table above.

What is the context window of MiniMax M2.5?

The largest context among free routes is 204,800 tokens. Some providers cap it lower.

How do I call MiniMax M2.5 via API?

Use any OpenAI-compatible client with base URL https://api.unorouter.com/v1, model ID minimax-m2.5:free, and a UnoRouter key.

How good is MiniMax M2.5?

Artificial Analysis Intelligence Index: 22.8, GPQA Diamond: 85%. For comparison, the strongest free model in the catalog right now is GLM 5.3 Flash.

Is MiniMax M2.5 open-weight?

Yes, the weights are published — you can download and run it locally, for example with Ollama or LM Studio.