Kimi K3 Flex
Kimi K3 on the flex tier: discounted, best-effort latency, requests may be held under load
Context
1,048,560
Max output
1,048,560
Input / 1M
$1.95
Output / 1M
$9.75
Providers
1
01Profile
Profile
Released
2026-07-16
Last updated
2026-07-16
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
1+ recent events since 2026-07-16
2026-08-27Addedneuralwattoffering→ new