All Models

Kimi K3

kimi-k3 Reasoning Tool Calling Attachments Open Weights Structured Output

Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work

Providers 14
Released Jul 16, 2026
Input Modalities text, image, video, pdf
Output Modalities text
Tarsk Use coding

Benchmarks

57.1
Intelligence Index
76.2
Coding Index

Available Providers (14)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Kimi For Coding k3 $0/MTok $0/MTok 1.0M 131.1K
Kenari kimi-k3 $0/MTok $0/MTok 1.0M 131.1K
CrossModel moonshot/kimi-k3 $3/MTok $15/MTok 1.0M 1.0M
LLM Gateway kimi-k3 $3/MTok $15/MTok 1.0M 131.1K
EmpirioLabs AI kimi-k3 $3/MTok $15/MTok 1M 131.1K
Moonshot AI (China) kimi-k3 $3/MTok $15/MTok 1.0M 131.1K
ClinePass cline-pass/kimi-k3 $3/MTok $15/MTok 1.0M 131.1K
Moonshot AI kimi-k3 $3/MTok $15/MTok 1.0M 131.1K
OpenRouter moonshotai/kimi-k3 $3/MTok $15/MTok 1.0M 1.0M
Vercel AI Gateway moonshotai/kimi-k3 $3/MTok $15/MTok 1M 131.1K
Cloudflare AI Gateway moonshotai/kimi-k3 $3/MTok $15/MTok 1.0M 131.1K
NovitaAI moonshotai/kimi-k3 $3/MTok $15/MTok 1.0M 1.0M
ZenMux moonshotai/kimi-k3 $3/MTok $15/MTok 1.0M 131.1K
Venice AI kimi-k3 $3.75/MTok $18.75/MTok 1M 131.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output