Published capabilities
- Tool calling
- Streaming
- Reasoning
Model ID : minimax-m3
Model ID
minimax-m3
Context window
204,800 tokens
Maximum output
204,800 tokens
Input / 1M tokens
0.24 USD
Output / 1M tokens
0.96 USD
Cache read / 1M tokens
$0.048
Cache write / 1M tokens
$0.28
Cache reads reuse stored tokens; cache writes create the provider cache.
Authorized plans : gold, bronze, silver, pro, business
This model is also available with credits without a subscription.
MiniMax M3 may be published with multiple API formats. Choose one of this page’s badges and keep that contract in your client, especially for tools and response blocks.
Prices and capabilities come from the current catalog. Badges do not replace testing your parameters; keep the key server-side and start with a short output limit.
Configure the OpenAI-compatible SDKcurl https://api.routerlab.ch/v1/chat/completions \
-H "Authorization: Bearer $ROUTERLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-m3","max_tokens":128,"messages":[{"role":"user","content":"Hello RouterLab"}]}'Related models
Audience measurement
Allow Google Analytics and RouterLab to measure public visits and link campaign sources to your signup? This is optional and can be changed at any time. If you decline, only anonymous visit totals are kept.