Kimi K2 Thinking

ChatInput: TextReleased Nov 6, 2025

Built by Moonshot AI · China · moonshot.ai

Reasoning (Thinking) specialized

How to use

model: "moonshot/kimi-k2-thinking"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "moonshot/kimi-k2-thinking",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

262K

Max output

262K

Input $/1M

$0.47

Output $/1M

$2.00

Features

Tool callingJSON

Serving providers

DeepInfraNovita

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

146.0

Terminal-BenchAgentic terminal tasks

35.7%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…