Kimi K3.1 Pro

What you can use today

Token prices measure the small pieces of text the model reads or produces. Capacity is the amount the service accepts in a request; check the limits below for any fallback to another model. A dash means the rate is unverified.

Exact catalog ID: moonshotai/kimi-k3.1-pro. Native Kimi always thinks, with low/high/max effort and max by default. OpenRouter separately lists a none option. Check the service you call instead of assuming the settings are interchangeable.

Available thinking settings: none, low, high, max. We do not yet have comparable independent results for these settings. The documented OpenRouter default is max when effort is omitted. A default is not a recommendation for every task.

Native access requires a successful top-up of at least $1. The publisher promises weights by November 4; a download is not yet verified.

This OpenRouter offer declares 1,048,576 context and 943,718 maximum output tokens. Thinking and the answer share the output budget.

OpenRouter lists $2 input, $0.20 cached input and $10 output per million tokens. These are hosted prices; a readable native price table was unavailable. Native batch processing is available at 60% of standard price for work that does not need an immediate response. This does not change the routed rate used in the calculator. Allow for retries and any tool fees. Models that think before answering may also charge for that work.

Provider release and specifications ↗

Inspect the exact catalog model ↗

Test it before switching

Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. A cheaper token price does not guarantee a cheaper completed task.