All Models

Kimi K2.6 (Tundra)

kimi-k2 Reasoning Tool Calling Open Weights

Multimodal Kimi workhorse for agent loops, coding tasks, and visual context

Providers 1
Released Apr 21, 2026
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

45.1
Intelligence Index
61.8
Coding Index

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
LLM Gateway tundra/kimi-k2.6 $0.40/MTok $2.20/MTok 262.1K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output