# MiniMax M2.5

> MiniMax's flagship M2.5 model (230B MoE, 10B active). Production-level agent model with function calling, structured output, and reasoning.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `minimax/minimax-m2.5`
- Status: available
- Released: 2026-02-12
- Context: 205K tokens
- Max output: 66K tokens
- Input: text; output: text
- Knowledge cutoff: 2025-06
- Capability score: 147 (as of 2026-11-02, see https://www.ohmygpt.com/rankings.md)
- Human preference rating (LMArena text): 1359

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $0.33 | per 1M tokens |
| Output | $1.32 | per 1M tokens |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:minimax/minimax-m2.5`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Amazon Bedrock | `bedrock:minimax/minimax-m2.5` | United States | $0.33 | $1.32 | no |

## Endpoints

| API | Request | model |
| --- | --- | --- |
| OpenAI Chat | POST https://api.ohmygpt.com/v1/chat/completions | `minimax/minimax-m2.5` |
| OpenAI Responses | POST https://api.ohmygpt.com/v1/responses | `minimax/minimax-m2.5` |
| Anthropic Messages | POST https://api.ohmygpt.com/v1/messages | `minimax/minimax-m2.5` |
| Google Gemini | POST https://api.ohmygpt.com/v1/models/minimax/minimax-m2.5:generateContent | `minimax/minimax-m2.5` |

## Example

```bash
curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2.5",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'
```

Web page: https://www.ohmygpt.com/models/minimax/minimax-m2.5