MiniMax M2.5

ChatInput: TextReleased Feb 12, 2026

Built by MiniMax · China · minimax.io

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...

How to use

model: "minimax/minimax-m2.5"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "minimax/minimax-m2.5",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

205K

Max output

197K

Input $/1M

$0.15

Output $/1M

$1.15

Features

Tool callingJSON

Serving providers

DeepInfraNovitaFriendliW&B Inference

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

147.1

Terminal-BenchAgentic terminal tasks

42.7%

ARC-AGI-2Abstract reasoning

4.9%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…