Skip to main content
Moonshot AI

Kimi K3.1 Pro Highspeed pricing, context window and limits

Kimi K3.1 Pro Highspeed costs $3.8874 per million input tokens and $20.3342 per million output tokens at Moonshot AI list price. It accepts up to 1,048,576 tokens of context and returns up to 1,048,576 tokens.

  • Model id kimi-k3.1-pro-highspeed
  • Snapshot

What does Kimi K3.1 Pro Highspeed cost?​

List prices in US dollars per million tokens
Input$3.8874
Output$20.3342
Cached input (read)$0.1944
Cache write$3.8874

US dollars per million tokens. A dash means no price is published.

How much can Kimi K3.1 Pro Highspeed read and write?​

Token limits
Context window1,048,576
Max output1,048,576

What can Kimi K3.1 Pro Highspeed do?​

Capabilities
Vision (image input)Yes
Tool callingYes
Structured outputYes
ReasoningYes
Inputtext, image, video
Outputtext

What does a request to Kimi K3.1 Pro Highspeed cost?​

Cost of example requests at list price, in US dollars
A typical request: 1,000 tokens in, 500 out$0.014
A long request: 10,000 tokens in, 1,000 out$0.059
1,000 typical requests$14.05
1 million tokens in and 1 million out$24.22

Input read from the provider's prompt cache costs $0.1944 per million tokens instead of $3.8874, 95% less. A request that repeats a 1,000-token prompt from the cache costs $0.01 instead of $0.014.

Among 6 Moonshot AI models with a published price, Kimi K3.1 Pro Highspeed is the 6th cheapest by input price. Its context window is the largest of 6. List prices only; discounts, batch prices and prices above 200K tokens are not shown.

How do I call Kimi K3.1 Pro Highspeed through DVARA?​

Configure the moonshot provider in the DVARA LLM Gateway and send the model id kimi-k3.1-pro-highspeed. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.

In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.

What should I check before relying on this data?​

The weekly review marked this entry. A person saw each mark and kept the model listed.

  • The cached-input price is outside the usual 10–50% of the input price.

Which other Moonshot AI models are there?​

All 6 Moonshot AI models · Search the full catalogue

Which models from other providers are similar to Kimi K3.1 Pro Highspeed?​

These are the closest in context window and input price, one per provider.

Snapshot 26 October 2026. DVARA reviews every price weekly before it is published. Get the whole catalogue as llm-models.json. Prices are list prices in US dollars per million tokens; check your provider contract before you budget.