MiniMax-M2.1 is a lightweight 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 capability while maintaining low latency, scalability, and cost efficiency. Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent brain for IDEs, coding tools, and general-purpose assistance. MiniMax recommends preserving reasoning between turns to avoid degrading the model's performance.
$0.15
$0.015
$0.60
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
MiniMax-M2.1 is a lightweight 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 capability while maintaining low latency, scalability, and cost efficiency.
On NagaAI, MiniMax M2.1 costs $0.15 per 1M input tokens and $0.60 per 1M output tokens. You pay only for what you use, with no subscription.
MiniMax M2.1 reads up to 196.6k tokens in one request, counting the prompt and the answer together.
Yes. MiniMax M2.1 can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.