> ## Documentation Index > Fetch the complete documentation index at: https://docs.pinkfish.ai/llms.txt > Use this file to discover all available pages before exploring further. # mistral-core > Mistral AI Core - chat completions, embeddings, models, files, and batch **Server path:** `/mistral-core` | **Type:** Application | **PCID required:** Yes ## Tools | Tool | Description | | ----------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- | | [`mistral_core_audio_api_v1_transcriptions_post`](#mistral_core_audio_api_v1_transcriptions_post) | Create Transcription | | [`mistral_core_chat_classifications_v1_chat_classifications_post`](#mistral_core_chat_classifications_v1_chat_classifications_post) | Chat Classifications | | [`mistral_core_chat_completion_v1_chat_completions_post`](#mistral_core_chat_completion_v1_chat_completions_post) | Chat Completion | | [`mistral_core_chat_moderations_v1_chat_moderations_post`](#mistral_core_chat_moderations_v1_chat_moderations_post) | Chat Moderations | | [`mistral_core_classifications_v1_classifications_post`](#mistral_core_classifications_v1_classifications_post) | Classifications | | [`mistral_core_create_voice_v1_audio_voices_post`](#mistral_core_create_voice_v1_audio_voices_post) | Create a new voice | | [`mistral_core_delete_model_v1_models_model_id_delete`](#mistral_core_delete_model_v1_models_model_id_delete) | Delete Model | | [`mistral_core_delete_voice_v1_audio_voices_voice_id_delete`](#mistral_core_delete_voice_v1_audio_voices_voice_id_delete) | Delete a custom voice | | [`mistral_core_embeddings_v1_embeddings_post`](#mistral_core_embeddings_v1_embeddings_post) | Embeddings | | [`mistral_core_files_api_routes_delete_file`](#mistral_core_files_api_routes_delete_file) | Delete File | | [`mistral_core_files_api_routes_download_file`](#mistral_core_files_api_routes_download_file) | Download File | | [`mistral_core_files_api_routes_get_signed_url`](#mistral_core_files_api_routes_get_signed_url) | Get Signed Url | | [`mistral_core_files_api_routes_list_files`](#mistral_core_files_api_routes_list_files) | List Files | | [`mistral_core_files_api_routes_retrieve_file`](#mistral_core_files_api_routes_retrieve_file) | Retrieve File | | [`mistral_core_files_api_routes_upload_file`](#mistral_core_files_api_routes_upload_file) | Upload File | | [`mistral_core_fim_completion_v1_fim_completions_post`](#mistral_core_fim_completion_v1_fim_completions_post) | Fim Completion | | [`mistral_core_get_voice_sample_audio_v1_audio_voices_voice_id_sample_get`](#mistral_core_get_voice_sample_audio_v1_audio_voices_voice_id_sample_get) | Get voice sample audio | | [`mistral_core_get_voice_v1_audio_voices_voice_id_get`](#mistral_core_get_voice_v1_audio_voices_voice_id_get) | Get voice details | | [`mistral_core_jobs_api_routes_batch_cancel_batch_job`](#mistral_core_jobs_api_routes_batch_cancel_batch_job) | Cancel Batch Job | | [`mistral_core_jobs_api_routes_batch_create_batch_job`](#mistral_core_jobs_api_routes_batch_create_batch_job) | Create Batch Job | | [`mistral_core_jobs_api_routes_batch_get_batch_job`](#mistral_core_jobs_api_routes_batch_get_batch_job) | Get Batch Job | | [`mistral_core_jobs_api_routes_batch_get_batch_jobs`](#mistral_core_jobs_api_routes_batch_get_batch_jobs) | Get Batch Jobs | | [`mistral_core_jobs_api_routes_fine_tuning_archive_fine_tuned_model`](#mistral_core_jobs_api_routes_fine_tuning_archive_fine_tuned_model) | Archive Fine Tuned Model | | [`mistral_core_jobs_api_routes_fine_tuning_unarchive_fine_tuned_model`](#mistral_core_jobs_api_routes_fine_tuning_unarchive_fine_tuned_model) | Unarchive Fine Tuned Model | | [`mistral_core_jobs_api_routes_fine_tuning_update_fine_tuned_model`](#mistral_core_jobs_api_routes_fine_tuning_update_fine_tuned_model) | Update Fine Tuned Model | | [`mistral_core_list_models_v1_models_get`](#mistral_core_list_models_v1_models_get) | List Models | | [`mistral_core_list_voices_v1_audio_voices_get`](#mistral_core_list_voices_v1_audio_voices_get) | List all voices | | [`mistral_core_moderations_v1_moderations_post`](#mistral_core_moderations_v1_moderations_post) | Moderations | | [`mistral_core_ocr_v1_ocr_post`](#mistral_core_ocr_v1_ocr_post) | OCR | | [`mistral_core_retrieve_model_v1_models_model_id_get`](#mistral_core_retrieve_model_v1_models_model_id_get) | Retrieve Model | | [`mistral_core_speech_v1_audio_speech_post`](#mistral_core_speech_v1_audio_speech_post) | Speech | | [`mistral_core_update_voice_v1_audio_voices_voice_id_patch`](#mistral_core_update_voice_v1_audio_voices_voice_id_patch) | Update voice metadata | *** ## mistral\_core\_audio\_api\_v1\_transcriptions\_post Create Transcription **Parameters:** | Parameter | Type | Required | Default | Description | | | ------------------------- | --------- | -------- | ------- | ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `context_bias` | string\[] | No | — | Context Bias | | | `diarize` | boolean | No | — | The diarize value | | | `file` | string | null | No | — | The File object (not file name) to be uploaded. To upload a file and specify a custom file name you should format your request as such: `bash file=@path/to/your/file.jsonl;filename=custom_name.jsonl ` Otherwise, you can just keep the original file name: `bash file=@path/to/your/file.jsonl ` | | `file_id` | string | null | No | — | ID of a file uploaded to /v1/files | | `file_url` | string | null | No | — | Url of a file to be transcribed | | `language` | string | null | No | — | Language of the audio, e.g. 'en'. Providing the language can boost accuracy. | | `model` | string | Yes | — | ID of the model to be used. | | | `stream` | boolean | No | — | The stream value | | | `temperature` | number | null | No | — | The temperature value | | `timestamp_granularities` | string\[] | No | — | Granularities of timestamps to include in the response. | | ````json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "context_bias": { "type": "array", "items": { "type": "string" }, "description": "Context Bias" }, "diarize": { "type": "boolean", "description": "The diarize value" }, "file": { "type": [ "string", "null" ], "description": "The File object (not file name) to be uploaded. To upload a file and specify a custom file name you should format your request as such: ```bash file=@path/to/your/file.jsonl;filename=custom_name.jsonl ``` Otherwise, you can just keep the original file name: ```bash file=@path/to/your/file.jsonl ```" }, "file_id": { "type": [ "string", "null" ], "description": "ID of a file uploaded to /v1/files" }, "file_url": { "type": [ "string", "null" ], "description": "Url of a file to be transcribed" }, "language": { "type": [ "string", "null" ], "description": "Language of the audio, e.g. 'en'. Providing the language can boost accuracy." }, "model": { "type": "string", "description": "ID of the model to be used." }, "stream": { "type": "boolean", "description": "The stream value" }, "temperature": { "type": [ "number", "null" ], "description": "The temperature value" }, "timestamp_granularities": { "type": "array", "items": { "type": "string", "enum": [ "segment", "word" ] }, "description": "Granularities of timestamps to include in the response." } }, "required": [ "PCID", "model" ] } ```` *** ## mistral\_core\_chat\_classifications\_v1\_chat\_classifications\_post Chat Classifications **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | --------- | -------- | ------- | ---------------- | | `input` | object\[] | Yes | — | Chat to classify | | `model` | string | Yes | — | The model value | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "input": { "type": "array", "items": { "type": "object", "properties": { "messages": { "type": "array", "description": "The messages value" } }, "required": [ "messages" ] }, "description": "Chat to classify" }, "model": { "type": "string", "description": "The model value" } }, "required": [ "PCID", "input", "model" ] } ``` *** ## mistral\_core\_chat\_completion\_v1\_chat\_completions\_post Chat Completion **Parameters:** | Parameter | Type | Required | Default | Description | | | --------------------- | --------- | -------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `frequency_penalty` | number | No | — | The `frequency_penalty` penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition. | | | `guardrails` | object\[] | No | — | A list of guardrail configurations to apply to this request. Each guardrail specifies a moderation type, categories with thresholds to evaluate, and an action to take on violation. | | | `max_tokens` | integer | null | No | — | The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. | | `messages` | any\[] | Yes | — | The prompt(s) to generate completions for, encoded as a list of dict with role and content. | | | `metadata` | object | No | — | The metadata value | | | `model` | string | Yes | — | ID of the model to use. You can use the List Available Models API to see all of your available models, or see our Model overview for model descriptions. | | | `n` | integer | null | No | — | Number of completions to return for each request, input tokens are only billed once. | | `parallel_tool_calls` | boolean | No | — | Whether to enable parallel function calling during tool use, when enabled the model can call multiple tools in parallel. | | | `prediction` | object | No | — | Enable users to specify an expected completion, optimizing response times by leveraging known or predictable content. | | | `presence_penalty` | number | No | — | The `presence_penalty` determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative. | | | `prompt_mode` | string | null | No | — | Allows toggling between the reasoning mode and no system prompt. When set to `reasoning` the system prompt for reasoning models will be used. **Deprecated for reasoning models - use `reasoning_effort` parameter instead.** | | `random_seed` | integer | null | No | — | The seed to use for random sampling. If set, different calls will generate deterministic results. | | `reasoning_effort` | string | No | — | Controls the reasoning effort level for reasoning models. "high" enables comprehensive reasoning traces, "none" disables reasoning effort. | | | `response_format` | object | No | — | Specify the format that the model must output. By default it will use `{ "type": "text" }`. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is in JSON. When using JSON mode you MUST also instruct the model to produce JSON yourself with a system or a user message. Setting to `{ "type": "json_schema" }` enables JSON schema mode, which guarantees the message the model generates is in JSON and follows the schema you provide. | | | `safe_prompt` | boolean | No | — | Whether to inject a safety prompt before all conversations. | | | `stop` | string\[] | No | — | Stop generation if this token is detected. Or if one of these tokens is detected when providing an array | | | `stream` | boolean | No | — | Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: \[DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON. | | | `temperature` | number | null | No | — | What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value. | | `tool_choice` | object | No | — | Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `any` or `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. | | | `tools` | object\[] | No | — | A list of tools the model may call. Use this to provide a list of functions the model may generate JSON inputs for. | | | `top_p` | number | No | — | 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. | | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "frequency_penalty": { "type": "number", "description": "The `frequency_penalty` penalizes the repetition of words based on their frequency in the generated text. A higher frequency penalty discourages the model from repeating words that have already appeared frequently in the output, promoting diversity and reducing repetition." }, "guardrails": { "type": "array", "items": { "type": "object", "properties": { "block_on_error": { "type": "boolean", "description": "If true, return HTTP 403 and block request in the event of a server-side error" }, "moderation_llm_v1": { "type": "object", "description": "Moderation Llm V1" }, "moderation_llm_v2": { "type": "object", "description": "Moderation Llm V2" } } }, "description": "A list of guardrail configurations to apply to this request. Each guardrail specifies a moderation type, categories with thresholds to evaluate, and an action to take on violation." }, "max_tokens": { "type": [ "integer", "null" ], "description": "The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length." }, "messages": { "type": "array", "description": "The prompt(s) to generate completions for, encoded as a list of dict with role and content." }, "metadata": { "type": "object", "description": "The metadata value" }, "model": { "type": "string", "description": "ID of the model to use. You can use the [List Available Models](/api/#tag/models/operation/list_models_v1_models_get) API to see all of your available models, or see our [Model overview](/models) for model descriptions." }, "n": { "type": [ "integer", "null" ], "description": "Number of completions to return for each request, input tokens are only billed once." }, "parallel_tool_calls": { "type": "boolean", "description": "Whether to enable parallel function calling during tool use, when enabled the model can call multiple tools in parallel." }, "prediction": { "type": "object", "description": "Enable users to specify an expected completion, optimizing response times by leveraging known or predictable content.", "properties": { "type": { "type": "string", "description": "The type value" }, "content": { "type": "string", "description": "The content value" } } }, "presence_penalty": { "type": "number", "description": "The `presence_penalty` determines how much the model penalizes the repetition of words or phrases. A higher presence penalty encourages the model to use a wider variety of words and phrases, making the output more diverse and creative." }, "prompt_mode": { "type": [ "string", "null" ], "description": "Allows toggling between the reasoning mode and no system prompt. When set to `reasoning` the system prompt for reasoning models will be used. **Deprecated for reasoning models - use `reasoning_effort` parameter instead.**", "enum": [ "reasoning" ] }, "random_seed": { "type": [ "integer", "null" ], "description": "The seed to use for random sampling. If set, different calls will generate deterministic results." }, "reasoning_effort": { "type": "string", "description": "Controls the reasoning effort level for reasoning models. \"high\" enables comprehensive reasoning traces, \"none\" disables reasoning effort.", "enum": [ "high", "none" ] }, "response_format": { "type": "object", "description": "Specify the format that the model must output. By default it will use `{ \"type\": \"text\" }`. Setting to `{ \"type\": \"json_object\" }` enables JSON mode, which guarantees the message the model generates is in JSON. When using JSON mode you MUST also instruct the model to produce JSON yourself with a system or a user message. Setting to `{ \"type\": \"json_schema\" }` enables JSON schema mode, which guarantees the message the model generates is in JSON and follows the schema you provide.", "properties": { "type": { "type": "string", "description": "The type value", "enum": [ "text", "json_object", "json_schema" ] }, "json_schema": { "type": "object", "description": "Json Schema" } } }, "safe_prompt": { "type": "boolean", "description": "Whether to inject a safety prompt before all conversations." }, "stop": { "type": "array", "items": { "type": "string" }, "description": "Stop generation if this token is detected. Or if one of these tokens is detected when providing an array" }, "stream": { "type": "boolean", "description": "Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON." }, "temperature": { "type": [ "number", "null" ], "description": "What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value." }, "tool_choice": { "description": "Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `any` or `required` means the model must call one or more tools. Specifying a particular tool via `{\"type\": \"function\", \"function\": {\"name\": \"my_function\"}}` forces the model to call that tool." }, "tools": { "type": "array", "items": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "function" ], "description": "The type value" }, "function": { "type": "object", "description": "The function value" } }, "required": [ "function" ] }, "description": "A list of tools the model may call. Use this to provide a list of functions the model may generate JSON inputs for." }, "top_p": { "type": "number", "description": "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." } }, "required": [ "PCID", "messages", "model" ] } ``` *** ## mistral\_core\_chat\_moderations\_v1\_chat\_moderations\_post Chat Moderations **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------ | -------- | ------- | ---------------- | | `input` | object | Yes | — | Chat to classify | | `model` | string | Yes | — | The model value | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "input": { "description": "Chat to classify" }, "model": { "type": "string", "description": "The model value" } }, "required": [ "PCID", "input", "model" ] } ``` *** ## mistral\_core\_classifications\_v1\_classifications\_post Classifications **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | --------- | -------- | ------- | ----------------------- | | `input` | string\[] | Yes | — | Text to classify. | | `metadata` | object | No | — | The metadata value | | `model` | string | Yes | — | ID of the model to use. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "input": { "type": "array", "items": { "type": "string" }, "description": "Text to classify." }, "metadata": { "type": "object", "description": "The metadata value" }, "model": { "type": "string", "description": "ID of the model to use." } }, "required": [ "PCID", "input", "model" ] } ``` *** ## mistral\_core\_create\_voice\_v1\_audio\_voices\_post Create a new voice **Parameters:** | Parameter | Type | Required | Default | Description | | | ------------------ | --------- | -------- | ------- | ------------------------- | ----------------------------------------- | | `age` | integer | null | No | — | The age value | | `color` | string | null | No | — | The color value | | `gender` | string | null | No | — | The gender value | | `languages` | string\[] | No | — | The languages value | | | `name` | string | Yes | — | The name value | | | `retention_notice` | integer | No | — | Retention Notice | | | `sample_audio` | string | Yes | — | Base64-encoded audio file | | | `sample_filename` | string | null | No | — | Original filename for extension detection | | `slug` | string | null | No | — | The slug value | | `tags` | string\[] | No | — | The tags value | | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "age": { "type": [ "integer", "null" ], "description": "The age value" }, "color": { "type": [ "string", "null" ], "description": "The color value" }, "gender": { "type": [ "string", "null" ], "description": "The gender value" }, "languages": { "type": "array", "items": { "type": "string" }, "description": "The languages value" }, "name": { "type": "string", "description": "The name value" }, "retention_notice": { "type": "integer", "description": "Retention Notice" }, "sample_audio": { "type": "string", "description": "Base64-encoded audio file" }, "sample_filename": { "type": [ "string", "null" ], "description": "Original filename for extension detection" }, "slug": { "type": [ "string", "null" ], "description": "The slug value" }, "tags": { "type": "array", "items": { "type": "string" }, "description": "The tags value" } }, "required": [ "PCID", "name", "sample_audio" ] } ``` *** ## mistral\_core\_delete\_model\_v1\_models\_model\_id\_delete Delete Model **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | ------------------------------ | | `model_id` | string | Yes | — | The ID of the model to delete. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "model_id": { "type": "string", "description": "The ID of the model to delete." } }, "required": [ "PCID", "model_id" ] } ``` *** ## mistral\_core\_delete\_voice\_v1\_audio\_voices\_voice\_id\_delete Delete a custom voice **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | ----------- | | `voice_id` | string | Yes | — | Voice Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "voice_id": { "type": "string", "description": "Voice Id" } }, "required": [ "PCID", "voice_id" ] } ``` *** ## mistral\_core\_embeddings\_v1\_embeddings\_post Embeddings **Parameters:** | Parameter | Type | Required | Default | Description | | | ------------------ | --------- | -------- | ------- | ----------------------- | ------------------------------------------------------------------------------------------------------------------------ | | `encoding_format` | string | No | — | Encoding Format | | | `input` | string\[] | Yes | — | Text to embed. | | | `metadata` | object | No | — | The metadata value | | | `model` | string | Yes | — | ID of the model to use. | | | `output_dimension` | integer | null | No | — | The dimension of the output embeddings when feature available. If not provided, a default output dimension will be used. | | `output_dtype` | string | No | — | Output Dtype | | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "encoding_format": { "type": "string", "description": "Encoding Format", "enum": [ "float", "base64" ] }, "input": { "type": "array", "items": { "type": "string" }, "description": "Text to embed." }, "metadata": { "type": "object", "description": "The metadata value" }, "model": { "type": "string", "description": "ID of the model to use." }, "output_dimension": { "type": [ "integer", "null" ], "description": "The dimension of the output embeddings when feature available. If not provided, a default output dimension will be used." }, "output_dtype": { "type": "string", "description": "Output Dtype", "enum": [ "float", "int8", "uint8", "binary", "ubinary" ] } }, "required": [ "PCID", "input", "model" ] } ``` *** ## mistral\_core\_files\_api\_routes\_delete\_file Delete File **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------ | -------- | ------- | ----------- | | `file_id` | string | Yes | — | File Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "file_id": { "type": "string", "description": "File Id" } }, "required": [ "PCID", "file_id" ] } ``` *** ## mistral\_core\_files\_api\_routes\_download\_file Download File **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------ | -------- | ------- | ----------- | | `file_id` | string | Yes | — | File Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "file_id": { "type": "string", "description": "File Id" } }, "required": [ "PCID", "file_id" ] } ``` *** ## mistral\_core\_files\_api\_routes\_get\_signed\_url Get Signed Url **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------- | -------- | ------- | --------------------------------------------------------------- | | `file_id` | string | Yes | — | File Id | | `expiry` | integer | No | — | Number of hours before the url becomes invalid. Defaults to 24h | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "file_id": { "type": "string", "description": "File Id" }, "expiry": { "type": "integer", "description": "Number of hours before the url becomes invalid. Defaults to 24h" } }, "required": [ "PCID", "file_id" ] } ``` *** ## mistral\_core\_files\_api\_routes\_list\_files List Files **Parameters:** | Parameter | Type | Required | Default | Description | | --------------- | --------- | -------- | ------- | -------------------------- | | `page` | integer | No | — | Page number for pagination | | `page_size` | integer | No | — | Number of results per page | | `include_total` | boolean | No | — | Include Total | | `sample_type` | string\[] | No | — | Sample Type | | `source` | string\[] | No | — | The source value | | `search` | string | No | — | The search value | | `purpose` | string | No | — | The purpose value | | `mimetypes` | string\[] | No | — | The mimetypes value | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "page": { "type": "integer", "description": "Page number for pagination" }, "page_size": { "type": "integer", "description": "Number of results per page" }, "include_total": { "type": "boolean", "description": "Include Total" }, "sample_type": { "type": "array", "items": { "type": "string", "enum": [ "pretrain", "instruct", "batch_request", "batch_result", "batch_error" ] }, "description": "Sample Type" }, "source": { "type": "array", "items": { "type": "string", "enum": [ "upload", "repository", "mistral" ] }, "description": "The source value" }, "search": { "type": "string", "description": "The search value" }, "purpose": { "type": "string", "description": "The purpose value", "enum": [ "fine-tune", "batch", "ocr" ] }, "mimetypes": { "type": "array", "items": { "type": "string" }, "description": "The mimetypes value" } }, "required": [ "PCID" ] } ``` *** ## mistral\_core\_files\_api\_routes\_retrieve\_file Retrieve File **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------ | -------- | ------- | ----------- | | `file_id` | string | Yes | — | File Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "file_id": { "type": "string", "description": "File Id" } }, "required": [ "PCID", "file_id" ] } ``` *** ## mistral\_core\_files\_api\_routes\_upload\_file Upload File **Parameters:** | Parameter | Type | Required | Default | Description | | | ------------ | ------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------- | | `expiry` | integer | null | No | — | The expiry value | | `file` | string | Yes | — | The File object (not file name) to be uploaded. To upload a file and specify a custom file name you should format your request as such: `bash file=@path/to/your/file.jsonl;filename=custom_name.jsonl ` Otherwise, you can just keep the original file name: `bash file=@path/to/your/file.jsonl ` | | | `purpose` | string | No | — | The purpose value | | | `visibility` | object | No | — | The visibility value | | ````json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "expiry": { "type": [ "integer", "null" ], "description": "The expiry value" }, "file": { "type": "string", "description": "The File object (not file name) to be uploaded. To upload a file and specify a custom file name you should format your request as such: ```bash file=@path/to/your/file.jsonl;filename=custom_name.jsonl ``` Otherwise, you can just keep the original file name: ```bash file=@path/to/your/file.jsonl ```" }, "purpose": { "type": "string", "description": "The purpose value", "enum": [ "fine-tune", "batch", "ocr" ] }, "visibility": { "description": "The visibility value" } }, "required": [ "PCID", "file" ] } ```` *** ## mistral\_core\_fim\_completion\_v1\_fim\_completions\_post Fim Completion **Parameters:** | Parameter | Type | Required | Default | Description | | | ------------- | --------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `max_tokens` | integer | null | No | — | The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length. | | `metadata` | object | No | — | The metadata value | | | `min_tokens` | integer | null | No | — | The minimum number of tokens to generate in the completion. | | `model` | string | Yes | — | ID of the model with FIM to use. | | | `prompt` | string | Yes | — | The text/code to complete. | | | `random_seed` | integer | null | No | — | The seed to use for random sampling. If set, different calls will generate deterministic results. | | `stop` | string\[] | No | — | Stop generation if this token is detected. Or if one of these tokens is detected when providing an array | | | `stream` | boolean | No | — | Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: \[DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON. | | | `suffix` | string | null | No | — | Optional text/code that adds more context for the model. When given a `prompt` and a `suffix` the model will fill what is between them. When `suffix` is not provided, the model will simply execute completion starting with `prompt`. | | `temperature` | number | null | No | — | What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value. | | `top_p` | number | No | — | 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. | | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "max_tokens": { "type": [ "integer", "null" ], "description": "The maximum number of tokens to generate in the completion. The token count of your prompt plus `max_tokens` cannot exceed the model's context length." }, "metadata": { "type": "object", "description": "The metadata value" }, "min_tokens": { "type": [ "integer", "null" ], "description": "The minimum number of tokens to generate in the completion." }, "model": { "type": "string", "description": "ID of the model with FIM to use." }, "prompt": { "type": "string", "description": "The text/code to complete." }, "random_seed": { "type": [ "integer", "null" ], "description": "The seed to use for random sampling. If set, different calls will generate deterministic results." }, "stop": { "type": "array", "items": { "type": "string" }, "description": "Stop generation if this token is detected. Or if one of these tokens is detected when providing an array" }, "stream": { "type": "boolean", "description": "Whether to stream back partial progress. If set, tokens will be sent as data-only server-side events as they become available, with the stream terminated by a data: [DONE] message. Otherwise, the server will hold the request open until the timeout or until completion, with the response containing the full result as JSON." }, "suffix": { "type": [ "string", "null" ], "description": "Optional text/code that adds more context for the model. When given a `prompt` and a `suffix` the model will fill what is between them. When `suffix` is not provided, the model will simply execute completion starting with `prompt`." }, "temperature": { "type": [ "number", "null" ], "description": "What sampling temperature to use, we recommend between 0.0 and 0.7. Higher values like 0.7 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. The default value varies depending on the model you are targeting. Call the `/models` endpoint to retrieve the appropriate value." }, "top_p": { "type": "number", "description": "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." } }, "required": [ "PCID", "model", "prompt" ] } ``` *** ## mistral\_core\_get\_voice\_sample\_audio\_v1\_audio\_voices\_voice\_id\_sample\_get Get voice sample audio **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | ----------- | | `voice_id` | string | Yes | — | Voice Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "voice_id": { "type": "string", "description": "Voice Id" } }, "required": [ "PCID", "voice_id" ] } ``` *** ## mistral\_core\_get\_voice\_v1\_audio\_voices\_voice\_id\_get Get voice details **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | ----------- | | `voice_id` | string | Yes | — | Voice Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "voice_id": { "type": "string", "description": "Voice Id" } }, "required": [ "PCID", "voice_id" ] } ``` *** ## mistral\_core\_jobs\_api\_routes\_batch\_cancel\_batch\_job Cancel Batch Job **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------ | -------- | ------- | ----------- | | `job_id` | string | Yes | — | Job Id | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "job_id": { "type": "string", "description": "Job Id" } }, "required": [ "PCID", "job_id" ] } ``` *** ## mistral\_core\_jobs\_api\_routes\_batch\_create\_batch\_job Create Batch Job **Parameters:** | Parameter | Type | Required | Default | Description | | | --------------- | --------- | -------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------- | | `agent_id` | string | null | No | — | In case you want to use a specific agent from the **deprecated** agents api for batch inference, you can specify the agent ID here. | | `endpoint` | string | Yes | — | The endpoint value | | | `input_files` | string\[] | No | — | The list of input files to be used for batch inference, these files should be `jsonl` files, containing the input data corresponding to the bory request for the batch inference in a "body" field. An example of such file is the following: `json {"custom_id": "0", "body": {"max_tokens": 100, "messages": [{"role": "user", "content": "What is the best French cheese?"}]}} {"custom_id": "1", "body": {"max_tokens": 100, "messages": [{"role": "user", "content": "What is the best French wine?"}]}} ` | | | `metadata` | object | No | — | The metadata of your choice to be associated with the batch inference job. | | | `model` | string | null | No | — | The model to be used for batch inference. | | `requests` | object\[] | No | — | The requests value | | | `timeout_hours` | integer | No | — | The timeout in hours for the batch inference job. | | ````json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "agent_id": { "type": [ "string", "null" ], "description": "In case you want to use a specific agent from the **deprecated** agents api for batch inference, you can specify the agent ID here." }, "endpoint": { "type": "string", "description": "The endpoint value", "enum": [ "/v1/chat/completions", "/v1/embeddings", "/v1/fim/completions", "/v1/moderations", "/v1/chat/moderations", "/v1/ocr", "/v1/classifications", "/v1/chat/classifications", "/v1/conversations", "/v1/audio/transcriptions" ] }, "input_files": { "type": "array", "items": { "type": "string", "format": "uuid" }, "description": "The list of input files to be used for batch inference, these files should be `jsonl` files, containing the input data corresponding to the bory request for the batch inference in a \"body\" field. An example of such file is the following: ```json {\"custom_id\": \"0\", \"body\": {\"max_tokens\": 100, \"messages\": [{\"role\": \"user\", \"content\": \"What is the best French cheese?\"}]}} {\"custom_id\": \"1\", \"body\": {\"max_tokens\": 100, \"messages\": [{\"role\": \"user\", \"content\": \"What is the best French wine?\"}]}} ```" }, "metadata": { "type": "object", "description": "The metadata of your choice to be associated with the batch inference job." }, "model": { "type": [ "string", "null" ], "description": "The model to be used for batch inference." }, "requests": { "type": "array", "items": { "type": "object", "properties": { "custom_id": { "type": "string", "description": "Custom Id" }, "body": { "type": "object", "description": "The body value" } }, "required": [ "body" ] }, "description": "The requests value" }, "timeout_hours": { "type": "integer", "description": "The timeout in hours for the batch inference job." } }, "required": [ "PCID", "endpoint" ] } ```` *** ## mistral\_core\_jobs\_api\_routes\_batch\_get\_batch\_job Get Batch Job **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------- | -------- | ------- | ---------------- | | `job_id` | string | Yes | — | Job Id | | `inline` | boolean | No | — | The inline value | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "job_id": { "type": "string", "description": "Job Id" }, "inline": { "type": "boolean", "description": "The inline value" } }, "required": [ "PCID", "job_id" ] } ``` *** ## mistral\_core\_jobs\_api\_routes\_batch\_get\_batch\_jobs Get Batch Jobs **Parameters:** | Parameter | Type | Required | Default | Description | | --------------- | --------- | -------- | ------- | -------------------------- | | `page` | integer | No | — | Page number for pagination | | `page_size` | integer | No | — | Number of results per page | | `model` | string | No | — | The model value | | `agent_id` | string | No | — | Agent Id | | `metadata` | object | No | — | The metadata value | | `created_after` | string | No | — | Created After | | `created_by_me` | boolean | No | — | Created By Me | | `status` | string\[] | No | — | The status value | | `order_by` | string | No | — | Order By | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "page": { "type": "integer", "description": "Page number for pagination" }, "page_size": { "type": "integer", "description": "Number of results per page" }, "model": { "type": "string", "description": "The model value" }, "agent_id": { "type": "string", "description": "Agent Id" }, "metadata": { "type": "object", "description": "The metadata value" }, "created_after": { "type": "string", "description": "Created After" }, "created_by_me": { "type": "boolean", "description": "Created By Me" }, "status": { "type": "array", "items": { "type": "string", "enum": [ "QUEUED", "RUNNING", "SUCCESS", "FAILED", "TIMEOUT_EXCEEDED", "CANCELLATION_REQUESTED", "CANCELLED" ] }, "description": "The status value" }, "order_by": { "type": "string", "description": "Order By", "enum": [ "created", "-created" ] } }, "required": [ "PCID" ] } ``` *** ## mistral\_core\_jobs\_api\_routes\_fine\_tuning\_archive\_fine\_tuned\_model Archive Fine Tuned Model **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | ------------------------------- | | `model_id` | string | Yes | — | The ID of the model to archive. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "model_id": { "type": "string", "description": "The ID of the model to archive." } }, "required": [ "PCID", "model_id" ] } ``` *** ## mistral\_core\_jobs\_api\_routes\_fine\_tuning\_unarchive\_fine\_tuned\_model Unarchive Fine Tuned Model **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | --------------------------------- | | `model_id` | string | Yes | — | The ID of the model to unarchive. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "model_id": { "type": "string", "description": "The ID of the model to unarchive." } }, "required": [ "PCID", "model_id" ] } ``` *** ## mistral\_core\_jobs\_api\_routes\_fine\_tuning\_update\_fine\_tuned\_model Update Fine Tuned Model **Parameters:** | Parameter | Type | Required | Default | Description | | | ------------- | ------ | -------- | ------- | ------------------------------ | --------------------- | | `model_id` | string | Yes | — | The ID of the model to update. | | | `description` | string | null | No | — | The description value | | `name` | string | null | No | — | The name value | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "model_id": { "type": "string", "description": "The ID of the model to update." }, "description": { "type": [ "string", "null" ], "description": "The description value" }, "name": { "type": [ "string", "null" ], "description": "The name value" } }, "required": [ "PCID", "model_id" ] } ``` *** ## mistral\_core\_list\_models\_v1\_models\_get List Models **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | ------------------ | | `provider` | string | No | — | The provider value | | `model` | string | No | — | The model value | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "provider": { "type": "string", "description": "The provider value" }, "model": { "type": "string", "description": "The model value" } }, "required": [ "PCID" ] } ``` *** ## mistral\_core\_list\_voices\_v1\_audio\_voices\_get List all voices **Parameters:** | Parameter | Type | Required | Default | Description | | --------- | ------- | -------- | ------- | ---------------------------------- | | `limit` | integer | No | — | Maximum number of voices to return | | `offset` | integer | No | — | Offset for pagination | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "limit": { "type": "integer", "description": "Maximum number of voices to return" }, "offset": { "type": "integer", "description": "Offset for pagination" } }, "required": [ "PCID" ] } ``` *** ## mistral\_core\_moderations\_v1\_moderations\_post Moderations **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | --------- | -------- | ------- | ----------------------- | | `input` | string\[] | Yes | — | Text to classify. | | `metadata` | object | No | — | The metadata value | | `model` | string | Yes | — | ID of the model to use. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "input": { "type": "array", "items": { "type": "string" }, "description": "Text to classify." }, "metadata": { "type": "object", "description": "The metadata value" }, "model": { "type": "string", "description": "ID of the model to use." } }, "required": [ "PCID", "input", "model" ] } ``` *** ## mistral\_core\_ocr\_v1\_ocr\_post OCR **Parameters:** | Parameter | Type | Required | Default | Description | | | ---------------------------- | ---------- | -------- | ------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | | `bbox_annotation_format` | object | No | — | Structured output class for extracting useful information from each extracted bounding box / image from document. Only json\_schema is valid for this field | | | `document` | object | Yes | — | Document to run OCR on | | | `document_annotation_format` | object | No | — | Structured output class for extracting useful information from the entire document. Only json\_schema is valid for this field | | | `document_annotation_prompt` | string | null | No | — | Optional prompt to guide the model in extracting structured output from the entire document. A document\_annotation\_format must be provided. | | `extract_footer` | boolean | No | — | Extract Footer | | | `extract_header` | boolean | No | — | Extract Header | | | `id` | string | No | — | The id value | | | `image_limit` | integer | null | No | — | Max images to extract | | `image_min_size` | integer | null | No | — | Minimum height and width of image to extract | | `include_image_base64` | boolean | null | No | — | Include image URLs in response | | `model` | string | null | Yes | — | The model value | | `pages` | integer\[] | No | — | Specific pages user wants to process in various formats: single number, range, or list of both. Starts from 0 | | | `table_format` | string | null | No | — | Table Format | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "bbox_annotation_format": { "type": "object", "description": "Structured output class for extracting useful information from each extracted bounding box / image from document. Only json_schema is valid for this field", "properties": { "type": { "type": "string", "description": "The type value", "enum": [ "text", "json_object", "json_schema" ] }, "json_schema": { "type": "object", "description": "Json Schema" } } }, "document": { "description": "Document to run OCR on" }, "document_annotation_format": { "type": "object", "description": "Structured output class for extracting useful information from the entire document. Only json_schema is valid for this field", "properties": { "type": { "type": "string", "description": "The type value", "enum": [ "text", "json_object", "json_schema" ] }, "json_schema": { "type": "object", "description": "Json Schema" } } }, "document_annotation_prompt": { "type": [ "string", "null" ], "description": "Optional prompt to guide the model in extracting structured output from the entire document. A document_annotation_format must be provided." }, "extract_footer": { "type": "boolean", "description": "Extract Footer" }, "extract_header": { "type": "boolean", "description": "Extract Header" }, "id": { "type": "string", "description": "The id value" }, "image_limit": { "type": [ "integer", "null" ], "description": "Max images to extract" }, "image_min_size": { "type": [ "integer", "null" ], "description": "Minimum height and width of image to extract" }, "include_image_base64": { "type": [ "boolean", "null" ], "description": "Include image URLs in response" }, "model": { "type": [ "string", "null" ], "description": "The model value" }, "pages": { "type": "array", "items": { "type": "integer" }, "description": "Specific pages user wants to process in various formats: single number, range, or list of both. Starts from 0" }, "table_format": { "type": [ "string", "null" ], "description": "Table Format", "enum": [ "markdown", "html" ] } }, "required": [ "PCID", "document", "model" ] } ``` *** ## mistral\_core\_retrieve\_model\_v1\_models\_model\_id\_get Retrieve Model **Parameters:** | Parameter | Type | Required | Default | Description | | ---------- | ------ | -------- | ------- | -------------------------------- | | `model_id` | string | Yes | — | The ID of the model to retrieve. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "model_id": { "type": "string", "description": "The ID of the model to retrieve." } }, "required": [ "PCID", "model_id" ] } ``` *** ## mistral\_core\_speech\_v1\_audio\_speech\_post Speech **Parameters:** | Parameter | Type | Required | Default | Description | | | ----------------- | ------- | -------- | ------- | ----------------------------- | --------------------------------------------------------------- | | `input` | string | Yes | — | Text to generate speech from. | | | `model` | string | null | No | — | The model value | | `ref_audio` | string | null | No | — | The base64-encoded audio reference for zero-shot voice cloning. | | `response_format` | string | No | — | Response Format | | | `stream` | boolean | No | — | The stream value | | | `voice_id` | string | null | No | — | The preset or custom voice to use for generating the speech. | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "input": { "type": "string", "description": "Text to generate speech from." }, "model": { "type": [ "string", "null" ], "description": "The model value" }, "ref_audio": { "type": [ "string", "null" ], "description": "The base64-encoded audio reference for zero-shot voice cloning." }, "response_format": { "type": "string", "description": "Response Format", "enum": [ "pcm", "wav", "mp3", "flac", "opus" ] }, "stream": { "type": "boolean", "description": "The stream value" }, "voice_id": { "type": [ "string", "null" ], "description": "The preset or custom voice to use for generating the speech." } }, "required": [ "PCID", "input" ] } ``` *** ## mistral\_core\_update\_voice\_v1\_audio\_voices\_voice\_id\_patch Update voice metadata **Parameters:** | Parameter | Type | Required | Default | Description | | | ----------- | --------- | -------- | ------- | ------------------- | ---------------- | | `voice_id` | string | Yes | — | Voice Id | | | `age` | integer | null | No | — | The age value | | `gender` | string | null | No | — | The gender value | | `languages` | string\[] | No | — | The languages value | | | `name` | string | null | No | — | The name value | | `tags` | string\[] | No | — | The tags value | | ```json theme={null} { "type": "object", "properties": { "PCID": { "type": "string", "description": "Pink Connect ID for the authenticated connection" }, "voice_id": { "type": "string", "description": "Voice Id" }, "age": { "type": [ "integer", "null" ], "description": "The age value" }, "gender": { "type": [ "string", "null" ], "description": "The gender value" }, "languages": { "type": "array", "items": { "type": "string" }, "description": "The languages value" }, "name": { "type": [ "string", "null" ], "description": "The name value" }, "tags": { "type": "array", "items": { "type": "string" }, "description": "The tags value" } }, "required": [ "PCID", "voice_id" ] } ```