MiniMaxAI / text-generation Open weights Also via API updated 2 weeks ago

MiniMax-M2.5

Name: MiniMax-M2.5
Price: 0.3 USD
Author: MiniMaxAI

Join Our 💬 WeChat 🧩 Discord community. MiniMax Code ⚡️ API MCP MiniMax Website 🤗 Hugging Face 🚀 Hugging Face API 🐙 GitHub 🤖️ ModelScope 📄 License: Modified-MIT

Params

228.7 B

Context

196,608

Downloads 30d

1.2 M

Likes

1,530

Licence: other Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 623 K in the last 30 days (107.6%)

1.4 M272 K

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f8_e4m3	230.1 GB	288.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 192K ctx	230.1 GB	1,076.9 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/minimax-m2-5
{
  "hf_id": "MiniMaxAI/MiniMax-M2.5",
  "params_b": 228.69,
  "context_length": 196608,
  "license": { "id": "other", "commercial": "unknown" },
  "downloads_30d": 1202828,
  "vram_estimates": [
    { "quant": "f8_e4m3", "gb": 288.0 }
  ],
  "updated_at": "2026-10-27T01:00:04Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.30

input / 1M

$1.20

output / 1M

$0.06

cached input / 1M

$1.50

1M in + 1M out

Context window: 65,536 tokens
Max output: 58,982 tokens
Providers: 5
Cheapest provider: Venice · $0.27 / $0.95
Best throughput: —
AA Intelligence / Coding / Agentic: — / — / —

✓ Tool calling ✓ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✓ Prompt caching

Specifications

Architecture: MiniMaxM2ForCausalLM
Parameters: 228.7 B
Tensor type: F8_E4M3
Context length: 196,608
Vocabulary: 200,064
Layers / heads: 62 / 48
Licence: other
First seen on the Hub: 2026-02-12
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative MiniMax-M2.5-NVFP4 nvidia 222 K

Compare with any text-generation model

Popular comparisons

DeepSeek-V3.2 7.6 M DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF 3.3 M DeepSeek-V4-Flash-0731 2.7 M gpt-oss-120b 2.4 M GLM-5.3-Flash-Maya-GGUF 1.2 M Hy3 1.2 M