# MiniMax M3 API on Boundless

> MiniMax's open-weight model for long-running coding agents that work with images and video, served on Boundless.

Page: https://boundless.network/models/minimax-m3

## Price per 1M tokens

| Input | Cached input | Output |
| --- | --- | --- |
| $0.28 | $0.06 | $1.10 |

## MiniMax M3 at a glance

MiniMax M3 is a 427B-parameter mixture-of-experts model with 23B active parameters. It works with text, images and video across a 1M-token context window, with benchmark results covering coding, tool use and multimodal tasks.

Source: https://inference.boundless.network/models/minimax-m3

- Developer: MiniMax
- Context window: 1M tokens
- Input: Text, image, video
- Capabilities: Reasoning, tool use, vision

## MiniMax M3 API pricing by provider

| Provider | Input | Cached | Output | Context |
| --- | --- | --- | --- | --- |
| Boundless | $0.28 | $0.06 | $1.10 | 1M |
| MiniMax (model creator) | $0.30 | $0.06 | $1.20 | 1M |
| DeepInfra | $0.28 | $0.06 | $1.10 | 524K |
| Together | $0.30 | $0.06 | $1.20 | 524K |
| Fireworks | $0.30 | $0.06 | $1.20 | 512K |

Prices per 1M tokens. Sources: OpenRouter (https://openrouter.ai/minimax/minimax-m3) and Vercel AI Gateway (https://vercel.com/ai-gateway/models/minimax-m3)

## Switch with a base URL and a key

1. Get an API key: Sign up in the console and create a key. No sales call. https://inference.boundless.network/api-keys
2. Point your SDK at Boundless: Change the base URL and key. For Anthropic SDKs, drop the /v1 and set max_tokens.

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-m3",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

More examples: https://inference.boundless.network/docs/quickstart

## FAQ

### How much does MiniMax M3 cost on Boundless?

$0.28 per 1M input tokens, $0.06 per 1M cached input tokens and $1.10 per 1M output tokens, billed from prepaid credits. Every response includes exact token counts, so any charge can be checked against these prices.

### What is MiniMax M3's context window on Boundless?

1M tokens, shared by the prompt and the reply. max_tokens can go up to that limit.

### Does MiniMax M3 support tool calling?

Yes. MiniMax M3 supports tool use and reasoning.

### Can I control how much MiniMax M3 reasons?

Yes. On chat completions, set reasoning_effort to none, low, medium or high, or leave it unset for the model's default. Size max_tokens for both the thinking and the reply.

### Can MiniMax M3 read images?

Yes. MiniMax M3 accepts text, image, video as input.

### What are the rate limits?

Each team has caps on tokens per minute, requests per minute and concurrent requests, shown on the usage page. Cached input doesn't count against them, and support can raise them for your team.

### Does Boundless store my prompts or outputs?

No. Boundless never stores prompts or outputs and never trains on them. It keeps only what billing needs: token counts, model, timestamp and cost.

### Can Boundless help me decide if MiniMax M3 fits my workload?

Yes. We test it against your current model on your own prompts, then tune and run it to your targets.

## Links

- Try it in the playground: https://inference.boundless.network/playground?model=minimax-m3
- Talk to an engineer: https://boundless.network/#get-access
- All models: https://boundless.network/models