> ## Documentation Index > Fetch the complete documentation index at: https://langtail.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Invoke Deployed Prompt > Get completion for stored prompt. The response format is the same as [OpenAI Chat completion response](https://platform.openai.com/docs/api-reference/chat/object). ## OpenAPI ````yaml POST /{workspace}/{project}/{prompt}/{environment} openapi: 3.0.0 info: version: 1.0.0 title: Langtail prompt endpoint servers: [] security: [] paths: /{workspace}/{project}/{prompt}/{environment}: post: description: >- Get completion for stored prompt. The response format is the same as [OpenAI Chat completion response](https://platform.openai.com/docs/api-reference/chat/object). parameters: - schema: type: string example: required: true description: Your Langtail API Key name: X-API-Key in: header - schema: type: string example: workspace required: true description: Your workspace URL slug name: workspace in: path - schema: type: string example: project required: true description: Your project URL slug name: project in: path - schema: type: string example: prompt required: true description: Your prompt URL slug name: prompt in: path - schema: type: string example: production required: true description: Your environment URL slug name: environment in: path requestBody: content: application/json: schema: type: object properties: variables: type: object description: >- A mapping of variable names to their values. Will be injected in your saved prompt template. additionalProperties: anyOf: - type: string example: variableName: Your Value messages: type: array items: type: object properties: role: type: string enum: - assistant - user - system - function - tool name: type: string content: anyOf: - type: string description: Text content nullable: false - type: array description: Mix of text and images. items: anyOf: - type: object properties: type: type: string enum: - text text: type: string required: - type - text - type: object properties: type: type: string enum: - image_url image_url: type: object properties: url: type: string detail: type: string enum: - auto - low - high default: auto required: - url - detail required: - type - image_url - nullable: true description: >- Can be omited if there is a `function_call` or `tool_calls` function_call: type: object properties: name: type: string arguments: type: string required: - name - arguments tool_calls: type: array items: type: object properties: id: type: string type: type: string enum: - function function: type: object properties: name: type: string arguments: type: string required: - name - arguments required: - id - type - function tool_choice: anyOf: - type: string enum: - auto - type: string enum: - none - type: object properties: type: type: string enum: - function function: type: object properties: name: type: string required: - name required: - type - function tool_call_id: type: string required: - role - content description: >- Additional messages. These will be appended to the Prompt Template. example: - role: user content: Hello stream: type: boolean example: false model: type: string description: Overrides the model of deployed prompt. max_tokens: type: number description: >- Overrides the max tokens of deployed prompt. The maximum number of tokens that can be generated in the completion. temperature: type: number description: >- Overrides the temperature of deployed prompt. What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. top_p: type: number description: >- Overrides the top_p of deployed prompt. An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. presence_penalty: type: number description: Overrides the presence_penalty of deployed prompt. frequency_penalty: type: number description: Overrides the frequency_penalty of deployed prompt. template: description: >- Overrides the stored template messages with custom template messages. type: array items: type: object properties: role: type: string enum: - assistant - user - system - function - tool name: type: string content: anyOf: - type: string description: Text content nullable: false - type: array description: Mix of text and images. items: anyOf: - type: object properties: type: type: string enum: - text text: type: string required: - type - text - type: object properties: type: type: string enum: - image_url image_url: type: object properties: url: type: string detail: type: string enum: - auto - low - high default: auto required: - url - detail required: - type - image_url - nullable: true description: >- Can be omited if there is a `function_call` or `tool_calls` function_call: type: object properties: name: type: string arguments: type: string required: - name - arguments tool_calls: type: array items: type: object properties: id: type: string type: type: string enum: - function function: type: object properties: name: type: string arguments: type: string required: - name - arguments required: - id - type - function tool_choice: anyOf: - type: string enum: - auto - type: string enum: - none - type: object properties: type: type: string enum: - function function: type: object properties: name: type: string required: - name required: - type - function tool_call_id: type: string required: - role - content tool_choice: description: Overrides the tool choice of deployed prompt. anyOf: - type: string enum: - auto - required - none - type: object properties: type: type: string enum: - function function: type: object properties: name: type: string required: - name required: - type - function response_format: description: Overrides the response format of deployed prompt. type: object properties: type: type: string enum: - json_object required: - type user: type: string description: A unique identifier representing your end-user example: user_123 doNotRecord: type: boolean description: >- If true, potentially sensitive data like the prompt and response will not be recorded in the logs example: false metadata: type: object additionalProperties: anyOf: - type: string - type: number description: Additional custom data that will be stored for this request example: my_identifier: my-custom-ID seed: type: number description: A seed is used to generate reproducible results example: 123 responses: '200': description: >- Chat completion response from OpenAI - see https://platform.openai.com/docs/api-reference/chat/object for more details. content: application/json: schema: type: object properties: id: type: string description: A unique identifier for the chat completion. object: type: string description: The object type, which is always `chat.completion`. created: type: number description: >- The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. choices: type: array items: type: object properties: index: type: number description: The index of the choice in the list of choices. x-internal-comment: 'Using enum as example: 0 was ignored' enum: - 0 message: type: object properties: role: type: string enum: - assistant description: The role of the author of this message. content: type: string nullable: true example: >- I'm sorry, but I'm not able to fulfill this request. required: - role - content finish_reason: type: string enum: - stop - length - tool_calls - content_filter - function_call description: >- The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. required: - index - message - finish_reason description: >- A list of chat completion choices. Can be more than one if `n` is greater than 1. required: - id - object - created - model - choices '400': description: Invalid request bodys content: application/json: schema: type: object properties: error: type: string enum: - Invalid request body issues: type: array items: type: object properties: code: type: string enum: - unrecognized_keys - invalid_type keys: type: array items: type: string path: type: array items: type: string message: type: string required: - code - keys - path - message required: - error - issues example: error: Invalid request body issues: - code: unrecognized_keys keys: - unknown_variable path: - variables message: 'Unrecognized key(s) in object: ''unknown_variable''' servers: - url: https://api.langtail.com ````