Moonshot AI

MoonshotAI: Kimi K3.1 Pro

moonshotai/kimi-k3.1-pro

Overview

About this model

Kimi K3.1 Pro is Moonshot AI's 3T-class multimodal reasoning model, upgraded from K3 for coding, tool use, and long-running agent workflows. It accepts text, images, and video and produces text within a 1,048,576-token context window. Reasoning is always enabled, with low, high, and max effort levels; max is the default. It supports streaming and JSON Schema structured output. The default generation limit is 131,072 tokens and can be set up to 1,048,576 tokens, subject to the context space remaining after the input.

Context window
1048576
Category
-
Last updated
2026-10-24
Providers
-

Performance

Usage and availability

Last 14 days
Total usage-Tokens
Requests-All requests
TTFT-Average response
Availability-Successful requests
Cache hit rate-Cache read / input
Requests over timeDaily volume
Availability over timeDaily success rate
Cache hit rateDaily cache reads

API endpoints

Availability

Providers

-
ProviderRoutePricingCache hitTTFTOutput speed (TPS)Availability
Provider performanceAll active provider routes

API access

Request example

Choose a protocol and copy a ready-to-run request.

cURL
POST/v1/responses