MiniMax-M2.5 Pricing, Benchmarks & Channels

MiniMax-M2.5 is a 2026-02-12 model from MiniMax featuring a 205K context window and extended reasoning capabilities. Lowest rate on OpenRouter ($0.27 in / $0.95 out per 1M tokens).

⚖️ Compare in Radar Workbench 🧮 Monthly Cost Simulator
Input Price / 1M
$0.3137
Output Price / 1M
$1.2549
Cache Read / 1M
$0.0314
Context Window
205K
Generation Speed
68 TPS
Access Grade
A · CN Direct

F.A.R.E. Four-Dimension Score Breakdown

A · Accurate (Capability) 65/100 · Elo 1408 F · Fast (Speed & Latency) 68 Token/s · TTFT 3076ms R · Reliable (Stability & Access) Grade A · CN Domestic / CN Direct E · Economical (Cost) $0.3137 in · $1.2549 out
Scenario Capability Breakdown (0–100):
💻 Coding
67/100
✍️ Writing
58/100
📚 Long-Doc RAG
63/100
👁️ Vision OCR
Text-only
F.A.R.E. CAPABILITY RADAR
A · Accurate F · Fast E · Economical R · Reachable

MiniMax-M2.5 Multi-Platform Price Comparison (7 Verified Channels)

All prices are in USD per 1M tokens. Domestic developers can prioritize channels marked "Direct in CN" for compliant access and local billing.

Platform / Gateway Network Access Input ($/1M) Output ($/1M) Cache Hit ($/1M) Billing & Notes Link
OpenRouter Lowest Price Direct in CN $0.27 $0.95 $0.03 Direct CN access · RMB billing Visit Official →
DeepInfra Global Network $0.15 $1.15 $0.03 Global cloud billing Visit Official →
Alibaba Cloud Bailian (CN) Direct in CN $0.3 $1.2 $0.075 Direct CN access · RMB billing Visit Official →
302.AI Gateway Direct in CN $0.3 $1.2 $0.075 Direct CN access · RMB billing Visit Official →
AWS Bedrock Global Network $0.3 $1.2 $0.075 Global cloud billing Visit Official →
Together AI Global Network $0.3 $1.2 $0.06 Global cloud billing Visit Official →
MiniMax CN Official Direct in CN $0.3137 $1.2549 $0.0314 Direct CN access · RMB billing Visit Official →

✅ Core Strengths & Ideal Workloads

  • Direct access in mainland China with RMB enterprise billing
  • Open weights available for private self-hosting (~20GB VRAM at INT4)

⚠️ Limitations & Practical Caveats

  • Direct access in China and globally; known for ultra-fast M3.1 text models and Hailuo video generation.
  • Extended thinking generates internal reasoning tokens (~1.8x output multiplier)