minimax-m3

ollama-cloud/minimax-m3 · family minimax-m3 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideo.

—Blended $/1M (3:1)

—Input $/1M

—Output $/1M

—1M in + 1M out

—Cache read $/1M

—Cheapest rank

Provider: Ollama Cloud (ollama-cloud)
Context: 512,000 tokens
Max output: 131,072 tokens
Capabilities: toolsreasoningtextimagevideo

Same model, other providers

“minimax-m3” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

Provider	Input	Output	Blended	Context
Nvidia	free	free	$0.00	1000k
Kenari	free	free	$0.00	512k
MiniMax Token Plan (minimax.io)	free	free	$0.00	1000k
MiniMax Token Plan (minimaxi.com)	free	free	$0.00	1000k
Deep Infra	$0.28	$1.1	$0.49	524k
Fireworks AI	$0.3	$1.2	$0.52	512k
OpenCode Go	$0.3	$1.2	$0.52	1000k
Nebius Token Factory	$0.3	$1.2	$0.52	1049k
Ollama Cloud (this)	—	—	—	512k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Ollama Cloud and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"minimax-m3","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):