Explore HyperCLOVA X SEED Think 14B

The conversation sent to the chat model in chronological order. Each JSON item contains a role and its text content.

Defines functions the model is allowed to request, including each function’s name, purpose, and JSON parameter schema. Supplying a tool does not execute it—the application must run the requested function and return its result to the model.

Forces the model to enter its reasoning path rather than deciding automatically. Use it for difficult multi-step tasks where extra deliberation is valuable, knowing that it can increase output tokens and response time.

Requests a direct answer without producing the model’s reasoning section. Enable it for simple tasks or lower latency; do not combine it with force reasoning because the two controls express opposite behavior.

Removes internal tokens such as beginning-of-sequence, end-of-sequence, padding, and chat-control markers from readable output. Keep it enabled for user-facing text; disable it only when inspecting the model’s exact token sequence.

Supplies one or more literal delimiters that stop generation when matched. The match is sensitive to exact spelling, spacing, and capitalization, so use distinctive sequences that are unlikely to appear naturally in the response.

Limits sampling at each step to the specified number of most likely next tokens. Smaller values make output more conservative, while larger values preserve more variety; zero commonly means that this filter is disabled.

Adjusts how strongly the model favors its most likely next token. Lower values produce more focused and repeatable output, while higher values allow less-likely choices and increase variety; it only has an effect when sampling is enabled.

Limits sampling to the smallest set of likely tokens whose probabilities add up to this value. Lower settings make output more focused, while a value near 1 keeps more alternatives available; it only affects sampled generation.

Changes the scores of tokens that already appeared in the generated text. Values above 1 discourage repeated words and loops, 1 leaves probabilities unchanged, and values below 1 make repetition more likely.

Caps the length of the generated response in tokens, which are pieces of words rather than whole words. The model can stop naturally before the limit, but a value that is too low may cut off the answer and a high value can increase latency and cost.