Ollama

Parámetros de entrada

• modelstringObligatorio

  Model name to use for generating responses

• thinkany

  Enables thinking output; accepts true/false or 'high'/'medium'/'low'

• toolsobject[]

  Optional function tools the model may call during chat

• formatany

  Format for response: 'json' or JSON schema object

• streamboolean

  Returns streamed partial responses; defaults to false

• optionsobject

  Runtime options controlling text generation (ModelOptions)

• logprobsboolean

  Returns log probabilities of output tokens

• messagesobject[]Obligatorio

  Chat history as message objects with role and content

• keep_aliveany

  Model keep-alive duration (e.g., '5m' or 0 to unload immediately)

• top_logprobsinteger

  Number of most likely tokens per position when logprobs enabled

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

• rawboolean

  When true, bypasses prompt templating and returns the raw response from the model. Use this for debugging or when you need full control over the prompt. Note: raw mode will not return a context.

• modelstringObligatorio

  Model name to use for generation. Examples: 'llama2', 'mistral', 'gemma3:4b'.

• thinkany

  Enables thinking output. Accepts true/false or 'high'/'medium'/'low' for verbosity level.

• formatany

  Structured output format. Use 'json' for JSON output or provide a JSON schema object.

• imagesstring[]

  Array of base64-encoded images for multimodal models.

• promptstring

  Text for the model to generate a response from. Required unless using raw mode with a complete prompt.

• streamboolean

  When true, returns partial responses as stream. Default is false for non-streaming responses.

• suffixstring

  Text that appears after the user prompt. Used for fill-in-the-middle models.

• systemstring

  System prompt for the model to generate a response from.

• optionsobject

  Runtime options for model generation behavior.

• logprobsboolean

  Whether to return log probabilities of output tokens.

• keep_aliveany

  Model keep-alive duration. Examples: '5m' for 5 minutes, 0 to unload immediately.

• top_logprobsinteger

  Number of most likely tokens to return at each position. Requires logprobs=true.

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

Sin parámetros.

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

• ninteger

  Number of chat completion choices to generate. Default: 1

• seedinteger

  Seed for reproducible outputs. Same seed with same parameters produces same results

• stopany

  Stop sequences where the API will stop generating further tokens. Can be a string or array of strings

• userstring

  Unique identifier for the end-user for monitoring and abuse detection

• modelstringObligatorio

  Model identifier to use for completion (e.g., 'llama2', 'mistral', 'gemma3:4b')

• toolsobject[]

  Array of tool/function definitions available for the model to call

• top_pnumber

  Nucleus sampling parameter. Alternative to temperature. Default: 1.0

• streamboolean

  Enable streaming responses. If true, tokens are sent as server-sent events. Default: false

• messagesobject[]Obligatorio

  Array of message objects representing the conversation history

• logit_biasobject

  Modify likelihood of specified tokens appearing in the completion. Map of token IDs to bias values (-100 to 100)

• max_tokensinteger

  Maximum number of tokens to generate in the completion

• temperaturenumber

  Sampling temperature for randomness (0-2). Higher values make output more random. Default: 1.0

• tool_choicestring

  Controls which tool the model should use ('none', 'auto', or specific tool name)

• stream_optionsobject

  Additional streaming options.

• response_formatobject

  Response format specification for structured outputs.

• presence_penaltynumber

  Penalize tokens that have appeared to encourage new topics (-2.0 to 2.0). Default: 0

• frequency_penaltynumber

  Penalize frequent tokens to reduce repetition (-2.0 to 2.0). Default: 0

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

• ninteger

  Number of completions to generate for the prompt. Default: 1

• echoboolean

  Returns the prompt embedded within the completion response. Default: false

• seedinteger

  Random seed for reproducible outputs. Same seed with same parameters should yield same result

• stopany

  Sequences where the model should stop generating. Can be a single string or array of strings

• userstring

  Unique identifier representing the end-user for tracking and abuse monitoring

• modelstringObligatorio

  Model identifier to use for completion (e.g., 'llama2', 'mistral', 'deepseek-v3.2')

• top_pnumber

  Nucleus sampling parameter controlling diversity (0-1). Recommended to alter either temperature or top_p, not both. Default: 1.0

• promptstringObligatorio

  Text prompt for completion generation. Note: Currently only accepts a string, not arrays

• streamboolean

  Enable streaming responses as Server-Sent Events. Default: false

• suffixstring

  Text that comes after the completion. Used for insertion mode

• best_ofinteger

  Generates multiple completions server-side and returns the best one. Default: 1

• logprobsinteger

  Number of log probabilities to return (up to 5)

• logit_biasobject

  Modify likelihood of specified tokens appearing. Maps token IDs to bias values (-100 to 100)

• max_tokensinteger

  Maximum number of tokens to generate in the completion. Total of prompt + max_tokens cannot exceed model's context length

• temperaturenumber

  Controls randomness in output (0-2). Lower values make output more focused, higher values more random. Default: 1.0

• stream_optionsobject

  Additional streaming options.

• presence_penaltynumber

  Penalizes tokens based on whether they appear in text so far (-2.0 to 2.0). Positive values encourage new topics. Default: 0

• frequency_penaltynumber

  Penalizes tokens based on frequency in text so far (-2.0 to 2.0). Positive values decrease repetition. Default: 0

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

Sin parámetros.

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

• modelstringObligatorio

  The name of the model to retrieve information about.

• verboseboolean

  When enabled, includes large verbose fields in the response.

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not

Parámetros de entrada

Sin parámetros.

Parámetros de salida

• dataobjectObligatorio

  Data from the action execution

• errorstring

  Error if any occurred during the execution of the action

• successfulbooleanObligatorio

  Whether or not the action execution was successful or not