Kimi-K2-Instruct-0905
Kimi model for long-context chat, coding, and agentic reasoning
Context
262,144
Max output
262,144
Input / 1M
$0.39
Output / 1M
$1.80
Providers
4
01Profile
Profile
Released
2025-09-04
Last updated
2025-09-25
Knowledge cutoff
2024-10
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 3 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2025-09-04
2026-09-03Contextnano-gptContext window256,000→ 262,144
2026-09-03Contextnano-gptMax output262,144→ 100,352
2026-08-03Price cutnano-gptoutput / 1M$2.00→ $1.80
2026-07-09DeprecatednvidiaStatus—→ deprecated
2026-06-23Removedsyntheticofferingremoved→ new
2026-06-13Removedsiliconflowofferingremoved→ new
2026-06-13Removedsiliconflow-cnofferingremoved→ new
2026-06-10Removedgroqofferingremoved→ new
2026-06-08Removedbasetenofferingremoved→ new
2026-06-08Removeddeepinfraofferingremoved→ new
2026-04-26Removedchutesofferingremoved→ new
2026-03-13DeprecatedbasetenStatus—→ deprecated