MiniMax M3 Thinking
MiniMax M3 is MiniMax's native multimodal model, with about 428B total parameters and roughly 23B active at once. It is built to take in text, image and video from the start of training, and it uses MiniMax Sparse Attention to keep long-horizon coding and agentic work efficient.
- Price per 1M tokens
- $0.35 / $1.50
- input / output
- Cached input
- $0.075
- per 1M tokens
- Context
- 512K tokens
- 80K max output
- Providers
- 2
Providers
Compare all 2 providers of MiniMax M3 Thinking by price, speed and uptime, and call any of them through one OpenAI-compatible API.
Provider prices are what each provider charges. You pay the price above until pass-through billing starts; then you pay the provider's price directly.
512K context · 80K max output
- 1 more provider through partner hosts · from $0.24 in · $1.01 out
Per 1M tokens: the provider's own price. Speed and uptime show here once measured. “Requests go here” marks where a request that names no provider goes now. Logos are trademarks of their owners.
Price history
API
curl https://api.opencheap.si/v1/chat/completions \
-H "Authorization: Bearer $OPENCHEAP_API_KEY" -H "Content-Type: application/json" \
-d '{ "model": "opencheap/minimax-m3:thinking", "messages": [{ "role": "user", "content": "Hi" }] }'