moonshotai/Kimi-K2-Thinking

text-to-text

Enables autonomous, step-by-step reasoning and orchestration of 200–300 tool calls for complex research, coding, and web tasks across long contexts.

Advanced settings to control the behavior of the model.

Temperature: 0.7

Controls randomness: 0 = deterministic, 2 = very creative

Max Tokens

Maximum length of the response (1-128000 tokens)