MarsCompute / marscompute/mimo-v2.6-flash-marscompute

MiMo V2.6 Flash - access through LLMTR

MiMo V2.6 Flash is Xiaomi's fast MiMo model for chat and coding, with a context window of about one million tokens. On this row thinking is switched off, so replies are direct. It takes and returns text only; tool calling, JSON response formats and `stop` are not supported. Without `max_tokens` a reply stops at 4,096 tokens; send `max_tokens` for longer replies.

Same model, other providers: Xiaomi MiMo · Heabsy

Technical specifications

Canonical IDmarscompute/mimo-v2.6-flash-marscompute
ProviderMarsCompute
Context window1,000,000 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

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

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.150000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.300000

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":"marscompute/mimo-v2.6-flash-marscompute","messages":[{"role":"user","content":"Hello"}]}'

Related models