Moonshot AI

Kimi K2 Thinking

moonshotai/kimi-k2-thinking

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Kimi K2 Thinking

reasoning open weights tools

Moonshot AI moonshotai/kimi-k2-thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Input $/1M: $0.60
Output $/1M: $2.50
Context: 262K
Max output: 100K
Released: Nov 6, 2025
Modalities: text

Intelligence index-

Coding index21

Agentic index-

Cached input reads $0.15 per 1M · weights on Hugging Face as moonshotai/Kimi-K2-Thinking

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Kimi K2 Thinking
targets:
  - id: kimi-k2-thinking
    kind: llm
    name: Kimi K2 Thinking
    metadata:
      model: moonshotai/kimi-k2-thinking          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.001550

Price among Moonshot AI models

Input list price per million tokens; Kimi K2 Thinking is the 3rd cheapest of 9 listed.

1
Kimi K2.5
$0.45
2
Kimi K2 0711
$0.57
3
Kimi K2 Thinking
$0.60
4
Kimi K2 0905
$0.60
5
Kimi K2.7 Code
$0.66
6
Kimi K2.6
$0.95
7
MoonshotAI Kimi Latest
$2.55
8
Kimi K3
$3.00
9
Kimi K3 (batch)
$3.00

More from Moonshot AI

Other models by the same vendor in the catalogue.