Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image/video understanding.
Added Jul 16, 2026
Model weightsContext Window
1.0M
Max Output
1.0M
Avg output tokens (7d)
934 tokens
Input Price (Auto)
$2.00/1M
Output Price (Auto)
$10.00/1M
Cache Read (Auto)
$0.20/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
43.8
Coding Index
76.2
Agentic Index
50.6
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
58.3%
Better than 89% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
24.8%
Better than 40% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1492 Elo
Better than 90% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1565 Elo
Better than 90% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
22.0%
Better than 83% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
88.7%
Better than 99% of models compared
Reasoning
HLE
Humanity's Last Exam
46.9%
Better than 96% of models compared
CritPt
Research-level physics reasoning
23.4%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
12.6%
Better than 74% of models compared
SciCode
Python programming for scientific computing
59.5%
Better than 97% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
47.6%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
53.2%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
93.5%
Better than 97% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
88.7%
Better than 99% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
53.2%
Last updated Sep 15, 2026
Artificial AnalysisProviders
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Related text models
Compare Kimi K3 with similar models from the same provider or model family.
Kimi K2.7 Code High-Speed
moonshotai/kimi-k2.7-code-highspeedKimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.
Kimi K2.7 Code
moonshotai/kimi-k2.7-codeKimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode; instant/non-thinking mode is not supported.
Kimi Latest
moonshotai/kimi-latestCompatibility alias that routes to the newest Kimi model. Currently routes to Kimi K3.
Kimi K2.6
moonshotai/kimi-k2.6Kimi K2.6 is an open-source, native multimodal agentic model built for long-horizon coding, coding-driven design, and large-scale task orchestration. It can turn simple prompts and visual inputs into production-ready interfaces and full-stack workflows, and is designed to coordinate complex multi-agent plans with thousands of steps across code, documents, and spreadsheets.
Kimi K2.6 Thinking
moonshotai/kimi-k2.6:thinkingKimi K2.6 Thinking is the reasoning-optimized K2.6 variant for deeper multi-step planning and execution. It is tuned for long-horizon coding and design workflows, including complex orchestration across many specialized sub-agents and autonomous end-to-end output generation.
Kimi K2.5
moonshotai/kimi-k2.5Kimi K2.5 is Moonshot AI's native multimodal model built on Kimi K2 with ~15T mixed visual and text tokens, delivering strong general reasoning, visual coding, and agentic tool-calling. This route uses instant (non-thinking) mode for faster responses.