All Models

Kimi K2.5 (DeepInfra)

kimi-k2 Reasoning Tool Calling Attachments Open Weights

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

Providers 1
Released Jan 1, 2026
Input Modalities text, image, video
Output Modalities text
Tarsk Use coding

Benchmarks

36
Intelligence Index
46.8
Coding Index

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
LLM Gateway deepinfra/kimi-k2.5 $0.45/MTok $2.25/MTok 256K 131.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output