MiniMax: MiniMax M2.1: AI model
MiniMax M2.1 is a lightweight 10B-active model for coding and agentic app development, with cleaner output and a ~200K context. Reachable from inside Iran through Hormouz.
- Context window:
- 204,800 tokens
- Input:
- $0.3/1M tokens
- Output:
- $1.2/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Thinking levels: Always thinks
MiniMax M2.1 is a lightweight successor in the M2 family, optimised for coding, agentic workflows and modern application development. With only about 10 billion activated parameters it keeps latency, scalability and cost in check while delivering a clear step up in real-world capability.
Compared with M2 it produces cleaner, more concise output and feels faster to respond. It shows leading multilingual coding results across major systems and application languages and works well as an agent "brain" for IDEs and coding tools. Its context window is around 200K tokens.
Pricing is usage-based: $0.3 per million input tokens and $1.2 per million output tokens. Hormouz provides stable access to MiniMax M2.1 from inside Iran, with no foreign credit card or circumvention tooling required.
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax/minimax-m2.1",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | MiniMax |
|---|---|
| Type | Text |
| Context window | 204,800 tokens |
| Pricing | $0.30/M in · $1.20/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax/minimax-m2.1",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="minimax/minimax-m2.1",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "minimax/minimax-m2.1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the MiniMax: MiniMax M2.1 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches MiniMax: MiniMax M2.1 and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does MiniMax M2.1 cost?
- Billing is usage-based: $0.3 per million input tokens and $1.2 per million output tokens. There is no fixed monthly fee. You pay only for what you use, at the rates shown in the Hormouz dashboard.
- How do I access MiniMax M2.1 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to MiniMax M2.1 from inside Iran, with no foreign credit card or circumvention tooling required.
- Is MiniMax M2.1 compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing OpenAI SDKs and code run without a rewrite.
- How does MiniMax M2.1 differ from M2?
- M2.1 keeps the lightweight ~10B-active design but produces cleaner, more concise output and responds faster. It leads on multilingual coding benchmarks and works well as an agent brain for IDEs and coding tools, with a context of about 200K tokens.
Updated 2026-10-13