GreenPT / greenpt/minimax-m3-eu

MiniMax M3 - access through LLMTR

MiniMax M3 is a reasoning model with a 1,000,000-token context window that accepts image input alongside text. It supports tool/function calling. Repeated prompt prefixes are served from a cache and those input tokens bill at a quarter of the normal input rate. The model reasons by default and those tokens bill as output; output costs five times input. Even for short answers and image questions, set `max_tokens` well above the answer you expect; a tight budget can leave the answer empty.

Same model, other providers: TensorX (EU) · MiniMax

Technical specifications

Canonical IDgreenpt/minimax-m3-eu
ProviderGreenPT
Context window1,000,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext, image

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.541871
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.135468
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$2.709353

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions   -H "Authorization: Bearer llmtr-your_key"   -H "Content-Type: application/json"   -d '{"model":"greenpt/minimax-m3-eu","messages":[{"role":"user","content":"Hello"}]}'

Related models