--- title: "List AI agents" method: GET path: "/ai_agents" tags: ["AI Studio"] --- # List AI agents `GET /ai_agents` Lists AI agents based on the provided parameters. ## Query parameters - `mode` string[] - `fields` string[] - `agent_state` string[] - `include_box_default` boolean - `marker` string - `limit` integer ## Response `200` A successful response including the agents list. - AiMultipleAgentResponse — The part of an API response that describes marker based pagination. - `limit` integer — The limit that was used for these entries. This will be the same as the `limit` query parameter unless that value exceeded the maximum value allowed. The maximum value varies by API. - `next_marker` string, nullable — The marker for the start of the next page of results. - `prev_marker` string, nullable — The marker for the start of the previous page of results. - `entries` AiSingleAgentResponseFull[], required — The list of AI Agents. - `id` string, required — The unique identifier of the AI Agent. - `type` 'ai_agent' — The type of agent used to handle queries. - `origin` string, required — The provider of the AI Agent. - `name` string, required — The name of the AI Agent. - `access_state` string, required — The state of the AI Agent. Possible values are: `enabled`, `disabled`, and `enabled_for_selected_users`. - `created_by` UserBase — A mini representation of a user, used when nested within another resource. - `id` string, required — The unique identifier for this user. - `type` 'user', required — The value will always be `user`. - `created_at` string, date-time — The ISO date-time formatted timestamp of when this AI agent was created. - `modified_by` UserBase — A mini representation of a user, used when nested within another resource. - `id` string, required — The unique identifier for this user. - `type` 'user', required — The value will always be `user`. - `modified_at` string, date-time — The ISO date-time formatted timestamp of when this AI agent was recently modified. - `icon_reference` string — The icon reference of the AI Agent. - `allowed_entities` AiAgentAllowedEntity[] — List of allowed users or groups. - union — The entity with type and ID. - object — A mini representation of a user, used when nested within another resource. - `id` string, required — The unique identifier for this user. - `type` 'user', required — The value will always be `user`. - object — A base representation of a group. - `id` string, required — The unique identifier for this object. - `type` 'group', required — The value will always be `group`. - `ask` AiStudioAgentAskResponse — The AI agent to be used to ask questions. - `type` 'ai_agent_ask', required — The type of AI agent used to ask questions. - `access_state` string, required — The state of the AI Agent capability. Possible values are: `enabled` and `disabled`. - `description` string, required — The description of the AI agent. - `custom_instructions` string, nullable — Custom instructions for the AI agent. - `suggested_questions` string[] — Suggested questions for the AI agent. If null, suggested question will be generated. If empty, no suggested questions will be displayed. - `long_text` AiStudioAgentLongTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `embeddings` object - `model` string — The model used for the AI agent for calculating embeddings. - `strategy` object - `id` string — The strategy used for the AI agent for calculating embeddings. - `num_tokens_per_chunk` integer — The number of tokens per chunk. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `basic_text` AiStudioAgentBasicTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `basic_image` AiStudioAgentBasicTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `spreadsheet` AiStudioAgentSpreadsheetToolResponse — The AI agent tool used to handle spreadsheets and tabular data. - `model` string — The model used for the AI agent for spreadsheets. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `warnings` string[] — Warnings concerning tool. - `long_text_multi` AiStudioAgentLongTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `embeddings` object - `model` string — The model used for the AI agent for calculating embeddings. - `strategy` object - `id` string — The strategy used for the AI agent for calculating embeddings. - `num_tokens_per_chunk` integer — The number of tokens per chunk. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `basic_text_multi` AiStudioAgentBasicTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `basic_image_multi` AiStudioAgentBasicTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `text_gen` AiStudioAgentTextGenResponse — The AI agent to be used to generate text. - `type` 'ai_agent_text_gen', required — The type of AI agent used for generating text. - `access_state` string, required — The state of the AI Agent capability. Possible values are: `enabled` and `disabled`. - `description` string, required — The description of the AI agent. - `custom_instructions` string, nullable — Custom instructions for the AI agent. - `suggested_questions` string[] — Suggested questions for the AI agent. If null, suggested question will be generated. If empty, no suggested questions will be displayed. - `basic_gen` AiStudioAgentBasicGenToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages aim at helping the LLM understand its role and what it is supposed to do. The input for `{current_date}` is optional, depending on the use. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When using the `prompt_template` parameter, you **must include** input for `{user_question}`. Inputs for `{current_date}` and `{content}` are optional, depending on the use. - `embeddings` object - `model` string — The model used for the AI agent for calculating embeddings. - `strategy` object - `id` string — The strategy used for the AI agent for calculating embeddings. - `num_tokens_per_chunk` integer — The number of tokens per chunk. - `content_template` string — How the content should be included in a request to the LLM. Input for `{content}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `extract` AiStudioAgentExtractResponse — The AI agent to be used for metadata extraction. - `type` 'ai_agent_extract', required — The type of AI agent to be used for metadata extraction. - `access_state` string, required — The state of the AI Agent capability. Possible values are: `enabled` and `disabled`. - `description` string, required — The description of the AI agent. - `custom_instructions` string, nullable — Custom instructions for the AI agent. - `long_text` AiStudioAgentLongTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `embeddings` object - `model` string — The model used for the AI agent for calculating embeddings. - `strategy` object - `id` string — The strategy used for the AI agent for calculating embeddings. - `num_tokens_per_chunk` integer — The number of tokens per chunk. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `basic_text` AiStudioAgentBasicTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. - `basic_image` AiStudioAgentBasicTextToolResponse — AI agent processor used to handle basic text. - `model` string — The model used for the AI agent for basic text. For specific model values, see the [available models list](https://developer.box.com/guides/box-ai/ai-models). - `num_tokens_for_completion` integer — The number of tokens for completion. - `llm_endpoint_params` union — The parameters for the LLM endpoint specific to a model. - object — AI LLM endpoint params OpenAI object. - `type` 'openai_params', required — The type of the AI LLM endpoint params object for OpenAI. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `frequency_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. - `presence_penalty` number, nullable — A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. - `stop` string, nullable — Up to 4 sequences where the API will stop generating further tokens. - object — AI LLM endpoint params Google object. - `type` 'google_params', required — The type of the AI LLM endpoint params object for Google. This parameter is **required**. - `temperature` number, nullable — The temperature is used for sampling during response generation, which occurs when `top-P` and `top-K` are applied. Temperature controls the degree of randomness in the token selection. - `top_p` number, nullable — `Top-P` changes how the model selects tokens for output. Tokens are selected from the most (see `top-K`) to least probable until the sum of their probabilities equals the `top-P` value. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - object — AI LLM endpoint params AWS object. - `type` 'aws_params', required — The type of the AI LLM endpoint params object for AWS. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - object — AI LLM endpoint params IBM object. - `type` 'ibm_params', required — The type of the AI LLM endpoint params object for IBM. This parameter is **required**. - `temperature` number, nullable — What sampling temperature to use, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. - `top_p` number, nullable — An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with `top_p` probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. - `top_k` number, nullable — `Top-K` changes how the model selects tokens for output. A low `top-K` means the next selected token is the most probable among all tokens in the model's vocabulary (also called greedy decoding), while a high `top-K` means that the next token is selected from among the three most probable tokens by using temperature. - `system_message` string — System messages try to help the LLM "understand" its role and what it is supposed to do. - `prompt_template` string — The prompt template contains contextual information of the request and the user prompt. When passing `prompt_template` parameters, you **must include** inputs for `{user_question}` and `{content}`. `{current_date}` is optional, depending on the use. - `is_custom_instructions_included` boolean — True if system message contains custom instructions placeholder, false otherwise. - `warnings` string[] — Warnings concerning tool. ## Other responses - `400` — An unexpected client error. - `500` — An unexpected server error. --- [API](https://skmtc.net/box/apis/platform-api.md) · [All operations](https://skmtc.net/box/apis/platform-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/box/platform-api/revisions/ba8f087e1a4d/schema)