MiniMax · live price
MiniMax M3 API pricing
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Small and cheap (under $1 per 1M)Tool callingReasoningimage inputvideo input
- Input
- $0.3
- per 1M tokens
- Output
- $1.20
- per 1M tokens
- Cached input
- $0.06
- per 1M tokens
- Context
- 1.0M
- 512K max output
List price from OpenRouter, which passes MiniMax's price through without markup. Refreshed hourly. Released May 31, 2026. Model id minimax/minimax-m3.
What MiniMax M3 costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$0.90
1,000 input + 500 output tokens each
1,000 RAG questions
$3.00
8,000 input + 500 output tokens each
100 coding-agent steps
$1.14
30,000 input + 2,000 output tokens each, no caching
MiniMax M3 price history
No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.
MiniMax M3 price by host
DeepInfra serves it below list price right now. Route to it to pay less on every token.
- DeepInfra$0.224 in · $0.88 out · 524K ctx · 100.0% uptime 24h
- CoreWeave$0.23 in · $0.96 out · 262K ctx · 97.2% uptime 24h
- Venice$0.3 in · $1.20 out · 524K ctx · 99.0% uptime 24h
- Parasail$0.3 in · $1.20 out · 1.0M ctx · 99.6% uptime 24h
- Featherless$0.55 in · $2.20 out · 262K ctx · 95.5% uptime 24h
Where to buy MiniMax credits for less
MiniMax M3 costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
MiniMax M3 cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$27.00/ month
Cheaper alternatives to MiniMax M3
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.15 | $0.6 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
| Qwen: Qwen3.8 Omni Flash | $0.15 | $0.47 |
| DeepSeek: DeepSeek V4.1 Flash | $0.05 | $0.199 |
Other MiniMax models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| MiniMax M2.7 | $0.6 | $1.80 |
| MiniMax M2.5 | $0.27 | $0.95 |
| MiniMax M3.1 Flash | $0.075 | $0.3 |