# MiniMax M3

MiniMax M3 costs $0.3 per 1M input tokens and $1.2 per 1M output tokens on LLM API, with a 1M-token context window.

Model ID: `minimax-m3` · MiniMax · Text generation · Released May 28, 2026
Updated: 2026-10-13
Canonical: https://llmapi.ai/models/minimax-m3/

- Input: $0.3 per 1M tokens
- Output: $1.2 per 1M tokens
- Cache read: $0.06 per 1M tokens
- Context: 1M tokens
- Max output: 1.05M tokens

## Pricing

Lowest price among 4 providers, after discounts.

| Price | Amount | Per |
| --- | --- | --- |
| Input | $0.3 | per 1M tokens |
| Output | $1.2 | per 1M tokens |
| Cache read | $0.06 | per 1M tokens |

**Volume pricing.** At higher monthly volume, MiniMax M3 may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Providers

Prices after each provider’s discount; the lowest in bold.

| Provider | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output |
| --- | --- | --- | --- | --- | --- |
| [MiniMax](https://llmapi.ai/providers/minimax/) | $0.6 | $2.4 | **$0.06** | 1M | 4K |
| [Novita AI](https://llmapi.ai/providers/novita/) | **$0.3** | **$1.2** | **$0.06** | 1M | 4K |
| [CanopyWave](https://llmapi.ai/providers/canopywave/) (−5%) | $0.3373 | $1.6862 | $0.0845 | 512K | 128K |
| [Nebius](https://llmapi.ai/providers/nebius/) | **$0.3** | **$1.2** | **$0.06** | 1.05M | 1.05M |

## Features

“Some providers”: not every provider of this model supports it.

- Tools: Yes
- Parallel tool calls: No
- Image input: Some providers
- Reasoning: Yes (Levels: low, medium, high)
- Prompt caching: Yes
- Structured outputs: Some providers
- JSON mode: Some providers
- Streaming: Yes
- Web search: Yes

## Call MiniMax M3

### Chat Completions (`POST /v1/chat/completions`)

Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Docs: [Chat Completions docs](https://docs.llmapi.ai/api/v1/chat/completions)

## More from MiniMax

- [MiniMax-M3.1-Flash](https://llmapi.ai/models/minimax-m3-1-flash/): $0.15 / $0.6 per 1M input / output
- [MiniMax M2.1 Lightning](https://llmapi.ai/models/minimax-m2-1-lightning/): $0.12 / $0.48 per 1M input / output
- [MiniMax M2.1](https://llmapi.ai/models/minimax-minimax-m2-1/): $0.27 / $1.1 per 1M input / output

Prices synced 2026-11-09.

Next step: [Get API key](https://app.llmapi.ai/signup)