Kimi K3.1 Pro
Next-gen Kimi K3.1 Pro flagship for deep agentic planning and long-context coding.
Upgraded Kimi K3.1 Pro flagship delivering enhanced multi-turn tool planning, whole-repository context retention, and multimodal analysis up to 1M tokens.
Improves upon Kimi K3 in autonomous multi-step coding sessions, maintaining coherent file edits and terminal debugging state across marathon agent runs.
Autonomous coding agentsDeep planningMultimodal repo contextLong-horizon agent loopsArchitectural refactorsMultimodal reviews
Strengths
Upgraded agentic coding accuracy, 1M context retention, multimodal text/image/video support.
Considerations
Use `kimi-k3.1-pro` for flagship Moonshot coding and verification tasks; switch to `kimi-k3.1-pro-highspeed` when stream speed dominates.
Live throughput history
source: status.ebotservers.comParameters1T
Context1M
Max output128K
Intelligence index33
TPS avg 24h0.0
TTFB p500 ms
Uptime100.0%
Call it
Other models from Moonshot AI
A new version of this page is available