MoonshotAI: Kimi K2 0711
moonshotai/kimi-k2- Modalities
- text->text
- In / out price
- $0.57 / $2.3
- Context
- 131K
- Released
- Jul 11, 2025
- Knowledge cutoff
- 2024-12-31
per 1M
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
Supported parameters
frequency_penaltyFrequency penalty
Lowers the chance of a token in proportion to how often it already appeared.
max_tokensMax tokens
Upper bound on generated tokens. Output stops at the limit.
presence_penaltyPresence penalty
Lowers the chance of any token that has already appeared.
repetition_penaltyRepetition penalty
Penalizes text that already appeared. Common on open models.
seedSeed
A fixed seed helps reproduce sampling. It does not guarantee byte-identical output.
stopStop
Stop when these strings are produced. A string or an array of strings.
temperatureTemperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.
tool_choiceTool choice
Whether to call a tool: auto, none, or a named function.
toolsTools
Function definitions the model may call via tool_calls.
top_kTop-K
Sample only from the K most likely tokens.
top_pTop-p
Sample only from tokens whose cumulative probability reaches top_p.