MiniMax M3 web search

MiniMax M3 has no web search of its own, so Opper's engine adds it with one tool entry. Pick an EU route and pin Jina or Searchbase, and the model, the query and every page it reads stay in Europe.

UseWeb searchwithin

Add web search to MiniMax M3

Set up with agents

Paste this into your coding agent (Claude Code, Cursor, Codex, and more) and it will set up and build with Opper for you.

Get your API key

In your code

1curl https://api.opper.ai/v3/compat/chat/completions \
2  -H "Authorization: Bearer $OPPER_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{"model": "deepinfra/MiniMaxAI/MiniMax-M3",
5       "messages": [{"role": "user", "content": "What changed in the news today?"}],
6       "tools": [{"type": "opper:web_search", "engine": "jina"}]}'

Where you can run it

MiniMax M3 runs on the routes below. Route only to EU providers and pin "engine": "jina" or "searchbase" when your data has to stay in Europe. One route also sells flex processing: the same model at another price, picked per request with service_tier. How service tiers work.

Provider	Region	Training	Input	Output	Cache read
Lyceum	EU	No	$0.40	$2.00	$0.10	Not offered on this route
TensorX	EU	No	$0.40	$2.00	$0.10	Not offered on this route
DeepInfra	US	No	$0.28	$1.10	$0.06
Novita	US	No	$0.30	$1.20	$0.06	Not offered on this route
Fireworks	Multi	No	$0.30	$1.20	$0.06	Not offered on this route
Infercom	Multi	No	$0.67	$2.69	$0.07	Not offered on this route
MiniMax	Multi	No	$0.30	$1.20	$0.06	Not offered on this route
Nebius	Multi	No	$0.30	$1.20	Input price	Not offered on this route
Tencent Cloud	Multi	No	$0.30	$1.20	$0.06	Not offered on this route

The model

MiniMax M3

by MiniMax

MiniMax M3: natively multimodal 428B Mixture-of-Experts model with ~23B active parameters, MiniMax Sparse Attention for long context, and 59.0% on SWE-Bench Pro