# MiniMax M3

MiniMax M3 is a language model from MiniMaxAI with a 512K-token context window. Provider list price is $0.30 per million input tokens and $1.20 per million output; on Allocate you pay $0.32 and $1.28 with the 7% transaction fee. It is a closed model served over API; the weights are not published.

## Pricing

| | Provider list | On Allocate |
| --- | --- | --- |
| Input, per M tokens | $0.30 | $0.32 |
| Output, per M tokens | $1.20 | $1.28 |
| Cached input, per M tokens | $0.06 | $0.064 |

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

## Facts

| Field | Value |
| --- | --- |
| Lab | MiniMaxAI |
| Modality | Language |
| Context window | 512K tokens |
| License | Proprietary API |
| Open weights | No |
| Fine-tunable | No |
| Catalog id | minimaxai/minimax-m3 |

## What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.30 + 350 × $1.20 = $780 a month. Billed on Allocate it is $834.60 with the 7% transaction fee.

## Common questions

### How much does MiniMax M3 cost per million tokens?

Provider list price is $0.30 per million input tokens and $1.20 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.32 in and $1.28 out.

### What context window does MiniMax M3 have?

524,288 tokens (512K). At roughly 0.75 words per token, that is about 393k words of English text per request.

### What does cached input cost on MiniMax M3?

$0.06 per million tokens at list ($0.064 billed). Repeated prompt prefixes, such as a stable system prompt or tool definitions, bill at this rate instead of the full input price.

### Can I fine-tune MiniMax M3?

No. MiniMax M3 is a closed model served over API; the weights are not published. If you want a model you can train and own, start from an open-weights base in the catalog and fine-tune that.

### How do I call MiniMax M3 on Allocate?

Send minimaxai/minimax-m3 in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.

---

[HTML page](https://allocate.network/models/minimaxai-minimax-m3) · [Machine-readable catalog](https://allocate.network/catalog.json)