MiniMax M2.7 Complete Guide — 90% of Claude Opus at 1/50th the Price (2026)
MiniMax M2.7 is a 230-billion-parameter MoE model that activates only 10 billion parameters per token. It scores 56.22% on SWE-Pro, runs at 100 tokens/second, and costs $0.30 per million input tokens. That’s 50x cheaper than Claude Opus.
Architecture
| Spec | Value |
|---|---|
| Total parameters | 230B |
| Active parameters | 10B per token (4.3% activation) |
| Architecture | Sparse MoE (256 experts, 8 active per token) |
| Layers | 62 |
| Context window | 200K tokens |
| Speed | ~100 tokens/second |
| Attention | Multi-head causal with RoPE + QK RMSNorm |
| License | Open weights |
The extreme sparsity (4.3% activation) is what makes M2.7 so cheap to run. Only 10B of 230B parameters compute for each token, but the model has access to the full 230B knowledge base through expert routing.
Benchmarks
| Benchmark | M2.7 | Claude Opus 4.6 | GPT-5.4 | DeepSeek V3 |
|---|---|---|---|---|
| SWE-Pro | 56.22% | 57.3% | 57.7% | ~54% |
| SWE-bench Verified | ~78% | 80.8% | — | 77.8% |
| Coding (Kilo Code test) | ~90% of Opus | Baseline | — | ~85% of Opus |
M2.7 is within 1-2 points of Claude Opus on SWE-Pro. In real-world coding tests, it delivers roughly 90% of Opus quality.
Pricing
| MiniMax M2.7 | Claude Opus | DeepSeek | GLM-5.1 | |
|---|---|---|---|---|
| Input | $0.30/1M | $15.00/1M | $0.27/1M | $1.00/1M |
| Output | $1.20/1M | $75.00/1M | $1.10/1M | $2.30/1M |
| Cost for 1hr coding | ~$0.50 | ~$25 | ~$0.45 | ~$2 |
M2.7 and DeepSeek are the two cheapest frontier-class models. M2.7 is slightly more expensive but faster (100 tok/s vs 60 tok/s).
The self-evolving feature
M2.7’s headline feature is “self-evolution” — it uses multi-agent collaboration internally to plan, execute, and refine tasks. In practice, this means it can:
- Break complex tasks into subtasks
- Execute them with different internal strategies
- Evaluate results and retry with different approaches
- Improve its output iteratively within a single session
This is similar to Kimi K2.5’s Agent Swarm but happens internally rather than through external parallel agents.
How to use M2.7
Via OpenRouter
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="your-openrouter-key"
)
response = client.chat.completions.create(
model="minimax/minimax-m2.7",
messages=[{"role": "user", "content": "Refactor this function to use async/await"}]
)See our OpenRouter guide for full setup.
With Aider
aider --model openrouter/minimax/minimax-m2.7See our Aider guide.
With OpenCode
opencode --model minimax/minimax-m2.7See our OpenCode guide.
Via MiniMax API directly
client = OpenAI(
base_url="https://api.minimax.chat/v1",
api_key="your-minimax-key"
)
response = client.chat.completions.create(
model="MiniMax-M2.7",
messages=[{"role": "user", "content": "Write a REST API in Express"}]
)When to use M2.7
Best for:
- Budget-conscious teams needing near-frontier quality
- High-volume coding tasks (the speed + low cost combo)
- Agentic workflows (self-evolving capability)
- Replacing expensive Claude Opus calls for routine work
Not ideal for:
- Tasks requiring absolute best quality (Claude Opus still leads by ~10%)
- Self-hosting (no open weights for local deployment yet)
- GDPR-sensitive workloads (Shanghai-based servers)
M2.7 vs M2.5
| M2.7 | M2.5 | |
|---|---|---|
| Released | March 2026 | February 2026 |
| SWE-bench | ~78% | 80.2% |
| SWE-Pro | 56.22% | — |
| Self-evolving | ✅ | ❌ |
| Speed | 100 tok/s | Slower |
| Price | $0.30/1M | $0.15/1M |
M2.5 actually scores higher on SWE-bench Verified but M2.7 has the self-evolving capability and is faster. For pure coding, M2.5 might be the better value at half the price.
Bottom line
MiniMax M2.7 is the best value proposition in AI coding right now. 90% of Claude Opus quality at 2% of the cost. If you’re using model routing (cheap model for routine work, expensive model for hard problems), M2.7 should be your cheap model.
FAQ
Is MiniMax M2.7 free?
MiniMax offers a free API tier with generous rate limits for development and testing. Production usage is paid but extremely affordable — roughly 2% of Claude Opus pricing for comparable quality on routine tasks.
What is self-evolving AI?
Self-evolving AI refers to M2.7’s ability to improve its own responses through iterative self-refinement during inference. The model evaluates and revises its outputs in real-time, producing higher quality results without additional training.
Can I run MiniMax locally?
No, MiniMax M2.7 is currently only available through MiniMax’s API and is not open-weight. You cannot download the model for local deployment.
How does MiniMax compare to DeepSeek?
M2.7 and DeepSeek V3 perform similarly on coding benchmarks, but M2.7 is significantly cheaper per token. DeepSeek offers open weights for self-hosting, while MiniMax is API-only but provides better cost efficiency for cloud usage.
Related: What is MiniMax? · MiniMax M2.7 vs Claude vs DeepSeek · How to Use MiniMax API · How to Reduce LLM API Costs