LLM parameter glossary
60 parameters appear across the catalog. This page defines each one, grouped by what it controls. Open any parameter for the full breakdown — its default, range, and conditions on every model that accepts it. Definitions come from the same community-maintained data as the JSON API.
Length
-
Max tokens
integer
max_tokens -
Maximum number of output tokens the model may generate.
127 models / Alibaba, Anthropic, Cohere, DeepSeek, MiniMax, Mistral, Nvidia, OpenAI, Perplexity, Z.ai
-
Max completion tokens
integer
max_completion_tokens -
Maximum number of output tokens the model may generate.
-
Stop sequence
string
stop -
Stops generation when this string is detected.
-
Max output tokens
integer
generationConfig.maxOutputTokens -
Maximum number of tokens to include in a response candidate.
-
Stop sequences
string
stop_sequences -
Stops generation when one of these sequences is detected; up to five are allowed.
-
Number of completions
integer
n -
How many chat completion choices to generate for the request.
-
Max output tokens
integer
max_output_tokens -
Upper bound for output tokens generated in the Responses API response.
Sampling
-
Temperature
number
temperature -
Controls randomness. Lower values make outputs more focused; higher values make them more varied.
143 models / Alibaba, Anthropic, Cohere, DeepSeek, Meta, MiniMax, Mistral, Moonshot AI, Nvidia, OpenAI, Perplexity, xAI, Xiaomi, Z.ai
-
Top P
number
top_p -
Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
134 models / Alibaba, Anthropic, DeepSeek, Meta, MiniMax, Mistral, Moonshot AI, Nvidia, OpenAI, Perplexity, xAI, Xiaomi, Z.ai
-
Top K
integer
top_k -
Limits token sampling to the top K most likely next tokens.
-
Frequency penalty
number
frequency_penalty -
Penalizes words based on how often they already appear in the generated text.
-
Presence penalty
number
presence_penalty -
Penalizes repeated words or phrases to encourage a wider variety of generated content.
-
Seed
integer
seed -
Seed used for best-effort deterministic sampling when reproducible outputs are desired.
-
Do sample
boolean
do_sample -
When false, the model uses greedy decoding and ignores temperature and top_p.
-
Random seed
integer
random_seed -
Seed used for deterministic sampling when reproducible outputs are desired.
-
Seed
integer
generationConfig.seed -
Optional seed used for decoding when reproducible sampling is desired.
-
Temperature
number
generationConfig.temperature -
Controls randomness. Lower values make outputs more focused; higher values make them more varied.
-
Top K
integer
generationConfig.topK -
Limits token sampling to the top K most likely next tokens.
-
Top P
number
generationConfig.topP -
Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
-
Top K
integer
extra_body.top_k -
Limits generation to the selected number of highest-probability tokens.
-
Top K
integer
k -
Limits sampling to the K most likely tokens; 0 disables top-k sampling.
-
Top P
number
p -
Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
-
Repetition penalty
number
repetition_penalty -
Penalizes tokens that have already appeared to reduce repetition in the output.
Reasoning
-
Thinking mode
enum
thinking.type -
Controls the Anthropic thinking mode values supported by this model.
62 models / Anthropic, Cohere, DeepSeek, Moonshot AI, Xiaomi, Z.ai
-
Reasoning effort
enum
reasoning_effort -
Controls how much reasoning the model should perform before producing an answer.
-
Budget tokens
integer
thinking.budget_tokens -
Maximum token budget Anthropic may use for extended thinking before producing the final answer.
-
Thinking display
enum
thinking.display -
Controls whether Anthropic returns summarized or omitted thinking content.
-
Effort
enum
output_config.effort -
Controls Anthropic response thoroughness and token spend.
-
Reasoning effort
enum
reasoning.effort -
Controls how much reasoning the model should perform before producing an answer.
-
Include thoughts
boolean
generationConfig.thinkingConfig.includeThoughts -
Controls whether Gemini returns available thought summaries in the response parts.
-
Reasoning summary
enum
reasoning.summary -
Controls the level of reasoning summary returned with the response.
-
Split reasoning
boolean
reasoning_split -
Returns the model's reasoning in a separate reasoning_details field instead of inline with the response.
-
Thinking budget
integer
generationConfig.thinkingConfig.thinkingBudget -
Number of thinking tokens Gemini should use; -1 uses dynamic thinking, 0 disables thinking, and fixed budgets start at 512 tokens.
-
Enable thinking
boolean
extra_body.chat_template_kwargs.enable_thinking -
Controls Qwen3 thinking mode when using OpenAI-compatible clients that pass provider-specific extra body fields.
-
Thinking level
enum
generationConfig.thinkingConfig.thinkingLevel -
Controls Gemini 3.1 Flash-Lite reasoning effort.
-
Reasoning budget
integer
reasoning_budget -
Maximum number of tokens the model may use for internal reasoning before being forced to end the reasoning trace. Use -1 to disable budget enforcement.
-
Prompt mode
enum
prompt_mode -
Enables Mistral's reasoning system prompt; leave unset to disable the default reasoning behavior.
-
Thinking token budget
integer
thinking.token_budget -
Maximum number of tokens the model may spend on reasoning before answering.
Tools
-
Tool choice
enum
tool_choice -
Forces the model to either call a tool or skip tool calls for this request.
Output
-
Response format
enum
response_format.type -
Forces the response into plain text or a JSON object.
59 models / Cohere, Meta, Mistral, Moonshot AI, xAI, Xiaomi, Z.ai
-
Response MIME type
enum
generationConfig.responseMimeType -
MIME type for generated text candidates.
-
Verbosity
enum
text.verbosity -
Controls how concise or detailed the model's final text response should be.
-
Text format
enum
text.format.type -
Controls whether the Responses API returns free-form text, JSON mode output, or structured JSON schema output.
Observability
-
Log probabilities
boolean
logprobs -
Controls whether the response includes log probabilities for the generated tokens.
Metadata
-
Safe prompt
boolean
safe_prompt -
Controls whether Mistral injects its safety prompt before the conversation.
-
Safety mode
enum
safety_mode -
Controls Cohere's built-in safety instructions applied to the generation.
-
Return images
boolean
return_images -
Controls whether the response may include related images from the search.
-
Return related questions
boolean
return_related_questions -
Controls whether the response includes suggested follow-up questions.
-
Search after date
string
search_after_date_filter -
Restricts search results to content published after this date (MM/DD/YYYY).
-
Search before date
string
search_before_date_filter -
Restricts search results to content published before this date (MM/DD/YYYY).
-
Search domain filter
string
search_domain_filter -
Limits search to, or excludes, specific domains.
-
Search mode
enum
search_mode -
Selects the corpus the model searches when grounding its answer.
-
Search recency filter
enum
search_recency_filter -
Restricts web search results to a recent time window.
-
Search context size
enum
web_search_options.search_context_size -
Controls how much web search context is retrieved before generating the answer.
-
Disable search
boolean
disable_search -
Turns off web search so the model answers from its own knowledge only.
-
Chunk length
integer
chunk_length -
Context window size for processing. Longer texts are automatically split into chunks with overlap for complete coverage. Must be greater than overlap.
-
Expert type
enum
expert_type -
The type of expert to use. 'knowledge' answers with USD knowledge, 'code' responds with vanilla OpenUSD code, 'helperfunction' uses high-level helper functions, and 'auto' lets the LLM determine which expert to use.
-
Flat NER
boolean
flat_ner -
When true, prevents overlapping entity spans. When false, may return nested entities such as both a full name and its constituent first name.