MiniMax M2.7

Tool callingReasoning

Hugging Face Launch post Website

Open MiniMax flagship for coding agents, office automation, and complex environments

Context: 205K
Released: 7mo ago
Parameters: 229B
Input / 1M tokens: $0.30
Output / 1M tokens: $1.20
Cached input / 1M tokens: $0.06

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
Terminal Bench	42.9% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · MiniMax-M2.7 Agent: Harness Agent https://www.tbench.ai/leaderboard/terminal-bench/2.0 Original-source terms apply
Terminal Bench	45.1% https://www.tbench.ai/leaderboard/terminal-bench/2.0 · MiniMax-M2.7 Agent: IndusAGI Coding Agent https://www.tbench.ai/leaderboard/terminal-bench/2.0 Original-source terms apply

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: MiniMax
Model family: MiniMax
Type: Language model
Predecessor: —
Successor: —
Released: March 18, 2026
Model ID: minimax/minimax-m2.7
Openness: Open weights
License: —
Parameters: 229B
Architecture: minimax-m2
Families: minimax-m2
Input modalities: text
Output modalities: text
Modality: text->text
Native context: 197K
Tokenizer: Other
Max output tokens: 131K
Hugging Face: MiniMaxAI/MiniMax-M2.7
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Open-weight builds

Ollama variants

Every published Ollama tag matched to this model, including parameter editions, instruction/base variants, and quantized builds.

1 builds

Variant	Parameters	Type	Quantization	Size	Context	Input
minimax-m2.7:cloud	229B	cloud	—	—	200K	text

Additional source evidence

Source model: minimax/MiniMax-M2.7
Source family: minimax
Last updated: 2026-03-18
Model context: 205K
Model output limit: 131K
Open weights: Yes
File attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Verified	79.9 · resolved	Claude Code · 2026-06-01	Source
SWE-Bench Pro	56.2 · resolve rate	Claude Code · 2026-06-01	Source
Terminal-Bench	51.1 · success rate	2.1 · 2026-06-01	Source

Complete source record (JSON)

{
  "id": "minimax/MiniMax-M2.7",
  "name": "MiniMax-M2.7",
  "description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
  "family": "minimax",
  "last_updated": "2026-03-18",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 204800,
    "output": 131072
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Verified",
      "score": 79.9,
      "source": "https://www.minimax.io/blog/minimax-m3",
      "metric": "resolved",
      "harness": "Claude Code",
      "date": "2026-06-01"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 56.2,
      "source": "https://www.minimax.io/blog/minimax-m3",
      "metric": "resolve rate",
      "harness": "Claude Code",
      "date": "2026-06-01"
    },
    {
      "name": "Terminal-Bench",
      "score": 51.1,
      "source": "https://www.minimax.io/blog/minimax-m3",
      "metric": "success rate",
      "version": "2.1",
      "date": "2026-06-01"
    }
  ],
  "release_date": "2026-03-18",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.7"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
GMICloud	gmicloud/fp8	197K	$0.21	$0.84	$0.04	—	99.71%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Novita	novita/fp8	205K	$0.27	$1.08	$0.05	—	99.82%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
AtlasCloud	atlas-cloud/fp8	197K	$0.30	$1.20	$0.06	—	99.17%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Minimax	minimax/fp8	205K	$0.30	$1.20	$0.06	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Groq	groq	197K	$0.60	$1.80	—	—	91.16%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Minimax	minimax/highspeed	205K	$0.60	$2.40	$0.06	—	98.12%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware