MiniMax: MiniMax M2✓ Catalog verified
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency. The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors. Benchmarked by Artificial Analysis, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency. To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.
Overview
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency. The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors. Benchmarked by Artificial Analysis, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency. To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns. Learn more about using reasoning_details to pass back reasoning in our docs.
Access: available through the official Minimax API. Context window: 197K.
Specifications
| API identifier | minimax/minimax-m2 |
| Provider | Minimax |
| Model type | Text LLM |
| Context window | 197K catalog |
| Input modalities | text |
| Output modalities | text |
| Released | Oct 23, 2025 |
| Moderated | No |
| Architecture modality | text->text |
API defaults
{
"top_p": 0.95,
"temperature": 1,
"frequency_penalty": null
}Pricing
Live pricing components for minimax/minimax-m2 as published in the catalog.
| Pricing component | Raw unit price | Normalized | Unit |
|---|---|---|---|
| Prompt tokens | $2.55e-7 | $0.26 / 1M | Per input token |
| Completion tokens | $0.000001 | $1.00 / 1M | Per output token |
| Request fee | N/A | N/A | Per request |
| Image fee | N/A | N/A | Per image unit |
| Web search fee | N/A | N/A | Per search request |
Cost calculator
Estimate monthly spend from your own token volumes.
Estimated Total Cost
$0.33Calculated from current list pricing in the ModelsAtlas catalog.Capabilities
| Capability | Status | What it means |
|---|---|---|
| Visual Understanding | Not advertised | Image and document analysis support |
| Audio Processing | Not advertised | Speech and voice aligned flows |
| Tool Calling | ✓ Supported | Supports tools / function calling |
| Self-Hosting | Not advertised | Deploy outside managed APIs |
Capability signals
Directional signals derived from model metadata and capability tags — not official benchmark submissions.
Quick start
Call MiniMax: MiniMax M2 through an OpenAI-compatible client.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="YOUR_API_KEY"
)
response = client.chat.completions.create(
model="minimax/minimax-m2",
messages=[{"role": "user", "content": "Explain quantum physics."}]
)
print(response.choices[0].message.content)Alternatives
Closest models by context window from a different provider.
| Model | Provider | Context | Input /1M | Actions |
|---|---|---|---|---|
| Anthropic: Claude 3 Haiku | Anthropic | 200K | $0.25 | View → |
| Anthropic: Claude 3.5 Haiku | Anthropic | 200K | $0.80 | View → |
Sources & attribution
Pricing and metadata are maintained in the ModelsAtlas catalog.
Frequently asked questions
How much does MiniMax: MiniMax M2 cost?
$0.26 per 1M input tokens and $1.00 per 1M output tokens on the official Minimax API.
What is the context window of MiniMax: MiniMax M2?
MiniMax: MiniMax M2 supports up to 197K tokens of context.
Does MiniMax: MiniMax M2 support tool / function calling?
Yes, MiniMax: MiniMax M2 supports tool / function calling — you can register tools and the model will emit structured tool calls.
How do I access MiniMax: MiniMax M2?
Use the official Minimax API with the model id `minimax/minimax-m2`. See the Quick start section above for code examples.