# MiniMaxAI/MiniMax-M2.5-TEE

> MiniMax-M2.5 is a frontier-class LLM excelling at coding, agentic tool use, and office automation tasks, with state-of-the-art performance on benchmarks like SWE-Bench while being dramatically more cost-effective than competitors.

This file is intended for AI coding agents wiring an application to this specific Chutes model.

## Important URLs

- Model page: https://chutes.ai/app/chute/chutes-minimaxai-minimax-m2-5-tee
- Model llms.txt: https://chutes.ai/app/chute/chutes-minimaxai-minimax-m2-5-tee/llms.txt
- Model OpenAPI 3.1 spec (this chute, callable): https://chutes.ai/app/chute/chutes-minimaxai-minimax-m2-5-tee/openapi.json
- Global Chutes llms.txt: https://chutes.ai/llms.txt
- Full Chutes docs export: https://chutes.ai/llms-full.txt
- Management API OpenAPI (account/billing/keys, NOT this model): https://api.chutes.ai/openapi.json

## Model Identifiers

- Name: `MiniMaxAI/MiniMax-M2.5-TEE`
- Chute ID: `ce6a92e4-5c2f-5681-9742-c80a4447bbdf`
- Slug: `chutes-minimaxai-minimax-m2-5-tee`
- Owner: `chutes`

## Authentication

- Use `Authorization: Bearer $CHUTES_API_KEY` for inference calls.
- Send JSON request bodies with `Content-Type: application/json` unless the endpoint documentation says otherwise.
- The request body is FLAT — send the request fields at the top level (no `input_args`/`args` wrapper).
- This model is served on the shared OpenAI-compatible gateway. Set the request `model` field to the exact Name above (`MiniMaxAI/MiniMax-M2.5-TEE`), and use base URL `https://llm.chutes.ai/v1`.
- For base64 media fields, send raw base64 strings in API requests. The web playground may use temporary Blob upload references internally for large files before proxying to Chutes.

## Endpoints

### 1. POST /v1/chat/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`
- Streaming: yes

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "MiniMaxAI/MiniMax-M2.5".
- `stream` (boolean, optional) Default: true.
- `messages` (array, optional) Default: [{"role":"user","content":""}].
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "MiniMaxAI/MiniMax-M2.5-TEE",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true,
  "max_tokens": 1024,
  "temperature": 0.7
}'
```

### 2. POST /v1/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`
- Streaming: yes

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "MiniMaxAI/MiniMax-M2.5".
- `prompt` (string, required)
- `stream` (boolean, optional) Default: true.
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "model": "MiniMaxAI/MiniMax-M2.5-TEE",
  "prompt": "a serene mountain lake at sunset",
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7,
  "min_p": 0,
  "top_k": -1,
  "top_p": 1,
  "logprobs": false,
  "ignore_eos": false,
  "min_tokens": 0,
  "top_logprobs": 0,
  "length_penalty": 1,
  "use_beam_search": false,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "repetition_penalty": 1,
  "skip_special_tokens": true,
  "include_stop_str_in_output": false,
  "spaces_between_special_tokens": true
}'
```

### 3. POST /v1/chat/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "MiniMaxAI/MiniMax-M2.5".
- `stream` (boolean, optional) Default: false.
- `messages` (array, optional) Default: [{"role":"user","content":""}].
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "MiniMaxAI/MiniMax-M2.5-TEE",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7
}'
```

### 4. POST /v1/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "MiniMaxAI/MiniMax-M2.5".
- `prompt` (string, required)
- `stream` (boolean, optional) Default: false.
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "model": "MiniMaxAI/MiniMax-M2.5-TEE",
  "prompt": "a serene mountain lake at sunset",
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7,
  "min_p": 0,
  "top_k": -1,
  "top_p": 1,
  "logprobs": false,
  "ignore_eos": false,
  "min_tokens": 0,
  "top_logprobs": 0,
  "length_penalty": 1,
  "use_beam_search": false,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "repetition_penalty": 1,
  "skip_special_tokens": true,
  "include_stop_str_in_output": false,
  "spaces_between_special_tokens": true
}'
```

### 5. GET /v1/models

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:


Example call:

```bash
curl -X GET "https://llm.chutes.ai/v1/models" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
```

## Model Facts

- Parameters: 229B total (safetensors weight count)
- Architecture: Mixture-of-Experts transformer (MiniMax-M2 family); 62 layers, 256 experts, 8 active per token
- Context length: 196,608 tokens
- Modalities: text in → text out
- Precision: FP8 (e4m3 block-quantized upstream weights), served in a TEE on Chutes
- License: Modified MIT
- Released: 2026-02
- Experts: 256 local experts, 8 active per token
- Layers: 62
- Hidden size: 3072
- Attention heads: 48
- Vocabulary: 200,064 tokens
- Training: RL across hundreds of thousands of real-world environments (200K+ coding environments, 10+ languages)
- Hugging Face: https://huggingface.co/MiniMaxAI/MiniMax-M2.5

## Recommended Parameters

- `temperature`: 1.0 (model-card recommendation; matches generation_config)
- `top_p`: 0.95 (model-card recommendation; matches generation_config)
- `top_k`: 40 (model-card recommendation; matches generation_config)

## Best For

- Coding agents: 80.2% SWE-Bench Verified and 51.3% Multi-SWE-Bench per the model card, with strong cross-harness generalization (79.7 on Droid, 76.1 on OpenCode)
- Agentic search and browsing: 76.3% BrowseComp with context management
- Office-work automation: Word, PowerPoint, and Excel financial modeling, trained with domain experts
- Full-lifecycle software development across 10+ languages, from system design to code review
- High-volume agent fleets where cost per task dominates: MiniMax positions M2.5 at a fraction of frontier-model cost

Not ideal for:

- Vision or audio input: text-only model
- Deep frontier math/knowledge reasoning: card-reported AIME25 86.3 and HLE-without-tools 19.4 trail the largest frontier models
- Strict-license environments: Modified MIT needs review before redistribution

## FAQ

### What context window does MiniMax M2.5 support?

196,608 tokens (192K), per max_position_embeddings in the upstream config. That is enough for repository-scale code context or long agent trajectories.

### How good is MiniMax M2.5 at coding?

The model card reports 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and strong cross-harness results (79.7 on Droid, 76.1 on OpenCode). It was trained on 200,000+ real-world coding environments across 10+ languages, covering the full development lifecycle rather than just bug fixing.

### Does it support function calling and tool use?

Yes. Agentic tool use is a core training target: MiniMax reports 76.3% on BrowseComp with context management and publishes a dedicated tool-calling guide in the repository. Send OpenAI-style tools through the gateway's chat completions endpoint.

### Can I use MiniMax M2.5 commercially?

The weights are released under a Modified MIT license (see the LICENSE file in the MiniMax-M2.5 GitHub repository). It is broadly permissive, but review the modifications before redistribution or large-scale commercial deployment.

### What does the TEE suffix mean?

The chute runs inference inside a Trusted Execution Environment, i.e. attested confidential-compute hardware. Prompts and outputs are processed inside the enclave. It is a serving-level property and does not change model outputs.

### How do I call it from the OpenAI SDK?

Point the client at base_url https://llm.chutes.ai/v1 with your Chutes API key and set model to MiniMaxAI/MiniMax-M2.5-TEE. Streaming is supported on chat and text completions.

### What sampling settings should I use?

MiniMax recommends temperature 1.0, top_p 0.95, and top_k 40, which match the repo's generation_config. The chute default temperature is 0.7, so pass the recommended values explicitly for reference behavior.

### Is M2.5 the same as M2.5-Lightning?

MiniMax describes M2.5 and M2.5-Lightning as identical in capability, differing only in serving speed and price on MiniMax's own platform. This chute serves the open-weights MiniMax-M2.5 release; throughput on Chutes is determined by Chutes' own serving infrastructure.


## Model Guide & Sources

- Full model guide: https://chutes.ai/docs/models/chutes-minimaxai-minimax-m2-5-tee
- Source: https://huggingface.co/MiniMaxAI/MiniMax-M2.5
- Source: https://huggingface.co/MiniMaxAI/MiniMax-M2.5/raw/main/config.json
- Source: https://huggingface.co/MiniMaxAI/MiniMax-M2.5/raw/main/generation_config.json
- Source: https://chutes.ai/app/chute/chutes-minimaxai-minimax-m2-5-tee/llms.txt

## Agent Integration Checklist

- Pick the endpoint path that matches the desired task.
- Set `CHUTES_API_KEY` in the server-side environment only.
- Validate required fields before sending requests.
- For media models, keep file upload, base64 conversion, and output preview/download handling explicit in the app UI.