Using Kimi K2 Thinking on NVIDIA NIM

Implementation guide · Kimi K2 · Moonshot AI

ServerlessOpen Source

NVIDIA NIM exposes Kimi K2 Thinking through model ID moonshotai/kimi-k2-thinking. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-04. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call moonshotai/kimi-k2-thinking — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricing

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

ReasoningStructured Outputs

About Kimi K2 Thinking

Extended thinking variant of Kimi K2 with native reasoning capabilities. 256K context.

Full model details →

Model Specs

Released2025-01-01
Parameters1T (32B active)
Context256k
ArchitectureDecoder Only

More Models on NVIDIA NIM

Kimi K2.6Kimi K2 InstructKimi K2 Instruct 0905
All models on NVIDIA NIM →

Also available on(6)

Fireworks AI$0.60/1MGCP Vertex AI$0.60/1MAWS Bedrock$0.60/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States