Kimi K3

deprecatedproprietary
Intelligence
Speed
Context
200K
Max context
1M
Input price
$3/1M tokens
Output price
$15/1M tokens

Capabilities

vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch

Details

Model IDkimi-k3
ProviderCursor
Familykimi-k3
Licenseproprietary
Parameters—
Statusdeprecated
Input modalitiestext, image
Output modalitiestext
Architecture—
Knowledge cutoff—
Training data cutoff—
Release date—
Deprecation date—
Typechat
Reasoning tokens—
Max input—
Open weightNo
Sourceofficial
Last updated

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$3
Output
$15
Cache write
—
Cache read
$0.3
Batch in
—
Batch out
—

Hidden by default; Requires Max Mode on legacy request-based plans; Up to 1M tokens with extended context at the same per-token rates (no long-context surcharge); No separate cache-write fee

Price across providers

ProviderInputOutputSince launch
Cursorcheapest$3$15—
Moonshot AI (Kimi)cheapest$3$15—
OpenCode Zencheapest$3$15—

API

GET/v1/models/cursor/kimi-k3