MiniMax M2.5
MiniMax M2.5 is served by 2 providers that kRouter can route to, with a 200K-token context window. Because more than one provider offers it, the price you pay depends on which one you route to — the same request, the same model, different bills.
Where to get MiniMax M2.5
| Provider | Route as |
|---|---|
| Command Code | commandcode/MiniMaxAI/MiniMax-M2.5 |
| SiliconFlow | siliconflow/MiniMaxAI/MiniMax-M2.5 |
What MiniMax M2.5 is suited for
A 200K window comfortably holds a long file plus its surrounding context, which covers most day-to-day coding turns without compaction. It supports extended reasoning, which helps on debugging and multi-step planning but spends output tokens on thinking before the answer appears — worth knowing when you set max_tokens. Tool and function calling are supported, so it can drive an agent loop.
Specs
- Context window
- 200K
- Max output
- 131K
- Input / 1M
- —
- Output / 1M
- —
- Extended reasoning
- Tool / function calling
MiniMax M2.5 FAQ
How much does MiniMax M2.5 cost?
MiniMax M2.5 has no published per-token rate here — it is served through plans or free tiers rather than metered billing.
Which providers serve MiniMax M2.5?
2 providers: Command Code, SiliconFlow. Through kRouter you can switch between them by changing the route prefix, without changing your tool.
What is MiniMax M2.5's context window?
200K tokens, with up to 131K tokens of output. kRouter publishes this on /v1/models as context_length, so clients read the real number instead of guessing from the model name.
Route to MiniMax M2.5 from any tool
kRouter runs locally and gives Claude Code, Cursor, Codex and the rest one endpoint that reaches every provider above — with automatic failover. Free and MIT-licensed.
Install kRouter