moonshotai/kimi-k2-thinking 🔢📝 → 📝

⭐ Official ▶️ 7.9K runs 📅 Nov 2025 ⚙️ Cog 0.23.0
code-generation question-answering reasoning text-generation thinking-model

Performance

5.4sTypical run time
~89sCold start (first call)
7.9KTotal runs

About

Kimi K2 Thinking is the latest, most capable version of an open-source thinking model.

Example Output

Prompt:

"How many r's are in the word 'strawberry'"

Output

There are 3 r's in the word "strawberry".

s-t-r-a-w-b-e-r-r-y

Performance Metrics

5.43s Prediction Time
88.72s Total Time
All Input Parameters 
{
  "top_p": 1,
  "prompt": "How many r's are in the word 'strawberry'",
  "max_tokens": 2048,
  "temperature": 0.1,
  "presence_penalty": 0,
  "frequency_penalty": 0
}
Input Parameters
top_p Type: numberDefault: 1
Top-p (nucleus) sampling
prompt Type: stringDefault:
Prompt
max_tokens Type: integerDefault: 2048
The maximum number of tokens the model should generate as output.
temperature Type: numberDefault: 0.1
The value used to modulate the next token probabilities.
presence_penalty Type: numberDefault: 0
Presence penalty
frequency_penalty Type: numberDefault: 0
Frequency penalty
Output Schema

Output

Type: array • Items Type: string

Version Details
Version ID
8af60bacd307bf8f41cfd02663d660ba28a267b616d2f44e6430194f3199dec7
Version Created
September 25, 2026
Run on Replicate →