OpenRouter — MiniMax M3.1 Flash (routed paid API, from rate)
OpenRouter lists MiniMax M3.1 Flash with provider-dependent pricing starting at USD $0.10 per 1M input tokens and $0.55 per 1M output tokens on the inference.net route; its cached-input rate is $0.01 per 1M on that provider. The model has a 1,048,576-token context, while the MiniMax and several other provider routes list $0.15 input and $0.60 output per 1M; the launch free offer ended October 22, 2026.
INPUT / 1M$0.10Native listed metric
OUTPUT / 1M$0.55Native listed metric
Pricing
Pricing details
Secondary price terms only; primary pricing stays in the deal summary.
CACHED / 1M$0.01When available
Fit & constraints
Fit & constraints
Use-case fit and limitations from the existing resource record.
AVAILABILITY
Available
Resource facts
Technical profile
Non-price resource facts only; pricing, history, and evidence stay in their own sections.
CONTEXT1.05M
AI MODELminimax/minimax-m3.1-flash
Trust layer
Verified evidence
Decision visuals remain traceable to the existing source and verification record.
Gemini 3.8 Live publishes audio input/output minute rates, while OpenAI splits voice pricing across GPT-Live-1, realtime models, transcription and translation. Compare the billing layers before estimating agent cost.