--- title: "Get App By Id" method: GET path: "/v1/apps/{app_id}" tags: ["apps"] --- # Get App By Id `GET /v1/apps/{app_id}` Retrieve an App by ID. ## Path parameters - `app_id` string, uuid, required ## Response `200` Successful Response - AppSettings - `main` AppSettingsData, required - `app` App, required - `auth0_id` string, required — The Auth0ID of the creator of the app - `modified_by` string, required — The Auth0ID of the last person to modify the table - `org_id` string, uuid — The Org to which this App belongs - `prompt_id` string, uuid, nullable — If any, the ID of the prompt associated with this app - `hashed_key` string, required — The hashed value of the API Key which we store in our database - `key_end` string, required — The last characters of the API key - `name` string, required — A name for this app - `description` string, nullable — A description for this app - `app_logo` string, nullable — A logo for this app - `is_active` boolean, required — True if the app is active (not soft-deleted, etc.), false otherwise - `rate_limit` integer - `has_failover_chain` boolean, required — A Failover chain, when enabled, skips the SMART router and instead calls the failover chain in order. - `weights` LLMModelWeights - `cost` number — Prioritizes cost when selecting the most optimized models for your use case. - `latency` number — Prioritizes latency and reduces the time delay between submitting a request and receiving the response. - `quality` number — Prioritizes the quality and readability of the generated responses. - `policies` LLMModelPolicies - `privacy_level` 1 | 2 | 3 — The level of privacy for a given request 0 = (UNSUPPORTED -- public logs) 1 = Log request, response and all of its metadata (Normal mode) 2 = Do not log neither the request prompt nor the response text. Logs are still visible, and all of the request metadata accessible. Retrievable as a log. (TBD) 3 = Do not log at all. Internally, a minimal representation may be stored for billing: model name, tokens used, which app it belongs to, and timestamp. Not retrievable as a log. (TBD) - `max_cost` number — The maximum cost allowed for a request. Only works with compounded requests that require multiple LLM calls. If the value is reached, it will exit with an exception. - `max_switch_model_retries` integer — If an LLM call fails, _how many other models_ should Pulze try, chosen by quality descending? It will be a maximum of N+1 models (original + N other models) - `max_same_model_retries` integer — If an LLM call fails, how many times should Pulze _retry the call to the same LLM_? There will be a maximum of N+1 calls (original + N retries) - `optimize_internal_requests` 0 | 1 — Optimize the internal / intermediate LLM requests, for a big gain in speed and cost savings, at the cost of a potential, and very slight, penalty on quality. The final request ("SYNTHESIZE") is always performed using your original settings. - `prompt_id` string, uuid, nullable — Prompt ID that we will use for requests - `settings` LLMModelSettings - `assistant_id` string, uuid, nullable - `assistant_version_id` string, uuid, nullable - `instructions` string, nullable - `max_tokens` integer - `temperature` number - `sandbox_of` string, uuid, nullable — The app might be a (testing) sandbox of a different App. - `use_parent_custom_data` boolean, nullable — If true, the app will use the custom data of the parent app - `added_on` string, date-time - `modified_on` string, date-time - `benchmark_model_id` string, uuid, required — Compare the results of LLMs against this model (for speed, quality, cost...) - `id` string, uuid, required - `benchmark_model` ModelData, required - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `prompt` Prompt, required - `prompt` string, required - `title` string, required - `description` string, required - `added_on` string, date-time, required - `modified_on` string, date-time, required - `org_id` string, uuid, required - `tokens` integer, required - `published_on` string, date-time, nullable, required - `reviewed_on` string, date-time, nullable, required - `approved_on` string, date-time, nullable, required - `decline_reason` string, nullable — Reason for decline - `id` string, uuid, required - `active_models` integer, required - `base_model_settings` PulzeModelActiveForApp[], required - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `id` string, uuid, nullable, required — Used to uniquely target models when we enable/disable them - `active` boolean — Whether the model is active for the app. - `globally_disabled` boolean, nullable — Whether the model is active for the org. - `custom_model_settings` PulzeModelActiveForApp[], required - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `id` string, uuid, nullable, required — Used to uniquely target models when we enable/disable them - `active` boolean — Whether the model is active for the app. - `globally_disabled` boolean, nullable — Whether the model is active for the org. - `failover_models` ModelData[], required - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `current_user_permissions` string[], nullable - `sandbox` AppSettingsData, required - `app` App, required - `auth0_id` string, required — The Auth0ID of the creator of the app - `modified_by` string, required — The Auth0ID of the last person to modify the table - `org_id` string, uuid — The Org to which this App belongs - `prompt_id` string, uuid, nullable — If any, the ID of the prompt associated with this app - `hashed_key` string, required — The hashed value of the API Key which we store in our database - `key_end` string, required — The last characters of the API key - `name` string, required — A name for this app - `description` string, nullable — A description for this app - `app_logo` string, nullable — A logo for this app - `is_active` boolean, required — True if the app is active (not soft-deleted, etc.), false otherwise - `rate_limit` integer - `has_failover_chain` boolean, required — A Failover chain, when enabled, skips the SMART router and instead calls the failover chain in order. - `weights` LLMModelWeights - `cost` number — Prioritizes cost when selecting the most optimized models for your use case. - `latency` number — Prioritizes latency and reduces the time delay between submitting a request and receiving the response. - `quality` number — Prioritizes the quality and readability of the generated responses. - `policies` LLMModelPolicies - `privacy_level` 1 | 2 | 3 — The level of privacy for a given request 0 = (UNSUPPORTED -- public logs) 1 = Log request, response and all of its metadata (Normal mode) 2 = Do not log neither the request prompt nor the response text. Logs are still visible, and all of the request metadata accessible. Retrievable as a log. (TBD) 3 = Do not log at all. Internally, a minimal representation may be stored for billing: model name, tokens used, which app it belongs to, and timestamp. Not retrievable as a log. (TBD) - `max_cost` number — The maximum cost allowed for a request. Only works with compounded requests that require multiple LLM calls. If the value is reached, it will exit with an exception. - `max_switch_model_retries` integer — If an LLM call fails, _how many other models_ should Pulze try, chosen by quality descending? It will be a maximum of N+1 models (original + N other models) - `max_same_model_retries` integer — If an LLM call fails, how many times should Pulze _retry the call to the same LLM_? There will be a maximum of N+1 calls (original + N retries) - `optimize_internal_requests` 0 | 1 — Optimize the internal / intermediate LLM requests, for a big gain in speed and cost savings, at the cost of a potential, and very slight, penalty on quality. The final request ("SYNTHESIZE") is always performed using your original settings. - `prompt_id` string, uuid, nullable — Prompt ID that we will use for requests - `settings` LLMModelSettings - `assistant_id` string, uuid, nullable - `assistant_version_id` string, uuid, nullable - `instructions` string, nullable - `max_tokens` integer - `temperature` number - `sandbox_of` string, uuid, nullable — The app might be a (testing) sandbox of a different App. - `use_parent_custom_data` boolean, nullable — If true, the app will use the custom data of the parent app - `added_on` string, date-time - `modified_on` string, date-time - `benchmark_model_id` string, uuid, required — Compare the results of LLMs against this model (for speed, quality, cost...) - `id` string, uuid, required - `benchmark_model` ModelData, required - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `prompt` Prompt, required - `prompt` string, required - `title` string, required - `description` string, required - `added_on` string, date-time, required - `modified_on` string, date-time, required - `org_id` string, uuid, required - `tokens` integer, required - `published_on` string, date-time, nullable, required - `reviewed_on` string, date-time, nullable, required - `approved_on` string, date-time, nullable, required - `decline_reason` string, nullable — Reason for decline - `id` string, uuid, required - `active_models` integer, required - `base_model_settings` PulzeModelActiveForApp[], required - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `id` string, uuid, nullable, required — Used to uniquely target models when we enable/disable them - `active` boolean — Whether the model is active for the app. - `globally_disabled` boolean, nullable — Whether the model is active for the org. - `custom_model_settings` PulzeModelActiveForApp[], required - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `id` string, uuid, nullable, required — Used to uniquely target models when we enable/disable them - `active` boolean — Whether the model is active for the app. - `globally_disabled` boolean, nullable — Whether the model is active for the org. - `failover_models` ModelData[], required - `supports_functions` boolean, required — True if the model supports `function`/`tool` call - `supports_json` boolean, required — True if the model supports `json`-formatted responses - `supports_n` boolean, required — True if the model supports `n` and `best_of` -- i.e, multiple responses - `supports_penalties` boolean, required — True if the model supports `frequency_penalty` and `presence_penalty` - `supports_stream` boolean, required — True if the model supports streaming responses - `supports_vision` boolean, required — True if the model supports image recognition (vision) - `completion_token_cost` number, required — The cost of a completion token, in USD - `prompt_token_cost` number, required — The cost of a prompt token, in USD - `base_cost` number, required — A (usually 0) cost added on top of a request. Some models charge per request, not only per token - `price_unit` 'tokens' | 'characters', required — The unit of billing for this model - `model` string, required — The name of the model. Can belong to many providers - `provider` string, nullable — The provider for the model. - `owner` string, nullable — The owner of the model. Sometimes, for a provider/model combination, many instances exist, trained on different data - `namespace` string, required — The fully qualified (namespaced) model name - `at` string, nullable — Extra model settings inferred from namespace - `context_window` integer, required — The max_tokens for this model - `until` string, date-time, nullable, required — The most recent data this model has been trained with - `description` string, required — A description of the model - `url` string, required — A URL to the model's page or more informatino - `api_target` string — Store the name of the model the API requires - `deprecated_on` string, date-time, nullable — For models whose deprecation date is known (past or future), to show errors and deny service, or show warnings - `parent_id` string, uuid, nullable — The ID of parent, in case it's not a base model - `parent` ModelData — recursive - `prompt_id` string, uuid, nullable — The ID of prompt, used for this model - `is_rag` boolean, required — Whether it's rag-tuned or not - `is_ft` boolean, required — Whether it's fine-tuned or not - `is_open_source` boolean, required — True if the model is open source - `is_gdpr` boolean, required — True if the model complies with GDPR - `is_chat` boolean, required — True if the model is of type Chat Completions, False if it's a Text Completion model. - `id` string, uuid, nullable, required — The ID of this model - `app_id` string, uuid, nullable, required — The app_id that has access to this model (if only one) - `org_id` string, uuid, nullable, required — The org_id that has acccess to this model - `added_by` string, nullable, required — The user (auth0_id) who created the model - `added_on` string, date-time, nullable, required — When the model was added. Auto-populated in DB - `modified_on` string, date-time, nullable, required — When the model was updated. Auto-populated in DB - `is_public` boolean, required — True if the model is publicly accessible to all - `is_test_model` boolean, required — Test models are only used for testing and do not perform any LLM requests - `is_pulze_owner` boolean, required — Model has been created and shared by Pulze - `default_active` boolean, required — This determines if the model will be available + pre-selected when users create new apps. - `current_user_permissions` string[], nullable - `sandbox_status` 'outdated', nullable, required ## Other responses - `422` — Validation Error --- [API](https://skmtc.net/pulze/apis/pulze-ai-api.md) · [All operations](https://skmtc.net/pulze/apis/pulze-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/pulze/pulze-ai-api/versions/a5e0b539abc5/schema)