> ## Documentation Index
> Fetch the complete documentation index at: https://docs.kymaapi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MiniMax

> MiniMax M2.5 and M2.7 — strong agentic coding and productivity models.

## Available models

| Model ID       | Parameters | Context | Speed  | Best For                                |
| -------------- | ---------- | ------- | ------ | --------------------------------------- |
| `minimax-m2.5` | —          | 196K    | Medium | Agentic coding, SWE-bench               |
| `minimax-m2.7` | —          | 205K    | Medium | Agentic coding, productivity, debugging |

## Why MiniMax?

MiniMax models are strong for real-world engineering and productivity workflows. They excel at:

* **Multi-file code editing** — understands project context across files
* **Bug fixing** — diagnoses and fixes real GitHub issues
* **Agentic workflows** — works well with tool use and multi-step coding tasks
* **Long context** — 196K tokens covers large codebases

## Recommendation

* **Use `minimax-m2.5`** when you want a proven SWE-bench-focused agentic coding model.
* **Use `minimax-m2.7`** when you want the newer MiniMax generation for agentic coding, debugging, and productivity workflows.

```python theme={null}
from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="minimax-m2.7",
    messages=[{"role": "user", "content": "Fix the race condition in this code: ..."}]
)
```