MiniMax

MiniMax-M2.5

MiniMaxAi/MiniMax-M2.5
Context

200K

Input

text

Output

text

Tool calling

Supported

About this model

MiniMax M2.5 is an open-source MoE model with 230B total parameters (10B active) and a 200K token context window, released February 2026 under a Modified MIT license. SOTA in coding, agentic tool use, search, and office work — scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp. Trained across 200K+ real-world RL environments in 10+ programming languages.Matches Claude Opus 4.6 speed while completing SWE-Bench 37% faster than M2.1.

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Available

Input tokens

$0.300 / 1M tokens

Output tokens

$1.200 / 1M tokens

Routing

OneInfer optimized

Available

Input tokens

$0.300 / 1M tokens

Output tokens

$1.200 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.300 / 1M tokens
Output tokens$1.200 / 1M tokens
Cached input tokens$0.060 / 1M tokens

Performance

Published evaluation results associated with this model.

SWE-bench

SWE-bench Verified80.2
Multi-SWE-bench51.3
SWE-bench Multilingual76.5

Coding

VIBE-Pro (Droid)79.7
VIBE-Pro (OpenCode)76.1

Search

BrowseComp76.3

API example

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMaxAi/MiniMax-M2.5",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'