# MiniMax M2.7

> Next-gen agentic productivity.

Human version: https://kymaapi.com/models/minimax-m2.7
Live JSON: `GET https://kymaapi.com/v1/models` (no auth required)

## Facts

- **Model ID**: `minimax-m2.7` — pass this as `model` in the request body
- **Creator**: MiniMax
- **Released**: 2026-03-18
- **Context window**: 205K tokens
- **Max output**: 33K tokens per response — a hard ceiling, not a default
- **Price**: $0.405 in / $1.62 out per 1M
- **Capabilities**: tools, reasoning

## Call it

```bash
curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "minimax-m2.7", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Positioning

MiniMax M2.7 is a text-only language model optimized for agentic workflows, coding, and debugging. Reach for it when you need reliable tool use and reasoning at a balanced cost tier.

## About

MiniMax M2.7 is a frontier-tier language model built by MiniMax for agentic productivity. It accepts text input and returns text output, with native support for tool calling, structured outputs, and explicit reasoning steps. It operates with a 204,800-token context window and a maximum output length of 32,768 tokens.

On Kyma, the model runs on an OpenAI-compatible endpoint and routes automatically through failover paths if a serving instance degrades. It delivers a median throughput of 15 tokens per second and maintains a 100% success rate across live traffic. Responses include exact token costs in the usage.cost field and identify the executed model via the X-Kyma-Model header.

The model does not support vision inputs or prompt caching. If your workflow relies on image analysis or requires cached prefix discounts, you will need to route elsewhere or structure prompts differently.

## Use cases

- **Agentic Workflow Orchestration** — Handles multi-step tool calls and state tracking for autonomous agents.
- **Code Generation and Debugging** — Writes, reviews, and fixes code across multiple languages with structured reasoning.
- **Productivity and Content Drafting** — Generates long-form text and organizes complex information within a large context window.
- **Structured Data Extraction** — Outputs strictly formatted JSON or XML for downstream parsing and API integration.

## Not ideal for

Do not use this model for tasks requiring image understanding, multimodal input, or prompt caching discounts.

## Pick something else when

- You need image or multimodal input → `gemini-3.6-flash`
- You want prompt caching to reduce prefix costs → `deepseek-v4-pro`

## See also

- All models: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md
- Other models by MiniMax: https://kymaapi.com/models?q=MiniMax