AI Models Directory
Nvidia
Nvidia
Open Source

Kimi K2 Thinking

A fast decision page for teams comparing performance, cost, context window, and critical capabilities without digging through raw specs.

Need a recommendation for your org?

Max Context (In)

262K

Max Output (Out)

262K

Input (1M tokens)

?

Output (1M tokens)

?

Quick signals

  • Provider: Nvidia
  • Inputs: text
  • Latest update: 2025-11

Usage profile

  • Context window: 262K
  • Max output: 262K
  • Open weights: Yes

Capabilities

Vision
Tool Calling
Structured Output (JSON)
File Attachments
Reasoning
Open Source

Related Models

Nemotron 3 Super

Nvidia · 262K

Llama Nemotron Embed VL 1B V2 (free)

Nvidia · 131K

Step 3.5 Flash

Nvidia · 256K

Kimi K2.5

Nvidia · 262K