> ## Documentation Index > Fetch the complete documentation index at: https://docs.passy.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Completion > Creates a completion for the provided prompt and parameters. This endpoint supports both streaming and non-streaming responses. ## OpenAPI ````yaml POST /completions openapi: 3.1.0 info: title: Passy API description: >- OpenAI-compatible API for accessing AI models through Passy. Unlimited AI for developers with predictable pricing. version: 1.0.0 contact: name: Passy Support email: hello@passy.ai url: https://passy.ai servers: - url: https://api.passy.ai/v1 description: Passy Production API security: - bearerAuth: [] tags: - name: Models description: List and retrieve information about available models - name: Completions description: Create text completions - name: Chat description: Create chat completions for conversational AI paths: /completions: post: tags: - Completions summary: Create Completion description: >- Creates a completion for the provided prompt and parameters. This endpoint supports both streaming and non-streaming responses. operationId: createCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CompletionRequest' examples: basic: summary: Basic completion request value: model: llama-3.3-70b-versatile prompt: Say this is a test max_tokens: 100 temperature: 0.7 streaming: summary: Streaming completion request value: model: gpt-4 prompt: Write a short story about AI max_tokens: 500 temperature: 0.8 stream: true responses: '200': description: Successfully created completion content: application/json: schema: $ref: '#/components/schemas/CompletionResponse' example: id: cmpl-7QyqpwdfhqwajicIEznoc6Q47XAyW object: text_completion created: 1677664795 model: llama-3.3-70b-versatile choices: - text: ' This is indeed a test' index: 0 logprobs: null finish_reason: stop usage: prompt_tokens: 5 completion_tokens: 7 total_tokens: 12 text/event-stream: schema: type: string description: Server-sent events stream when stream=true example: > data: {"id":"cmpl-7QyqpwdfhqwajicIEznoc6Q47XAyW","object":"text_completion","created":1677664795,"choices":[{"text":" This","index":0,"logprobs":null,"finish_reason":null}],"model":"llama-3.3-70b-versatile"} data: {"id":"cmpl-7QyqpwdfhqwajicIEznoc6Q47XAyW","object":"text_completion","created":1677664795,"choices":[{"text":" is","index":0,"logprobs":null,"finish_reason":null}],"model":"llama-3.3-70b-versatile"} data: [DONE] '400': description: Bad request - Invalid parameters content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 'Invalid value for ''temperature'': must be between 0 and 2' type: invalid_request_error code: invalid_parameter '401': description: Authentication failed - Invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Invalid API key provided type: invalid_request_error code: invalid_api_key '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Rate limit exceeded. Please try again later. type: rate_limit_error code: rate_limit_exceeded '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: CompletionRequest: type: object required: - model - prompt properties: model: type: string description: ID of the model to use example: llama-3.3-70b-versatile prompt: oneOf: - type: string - type: array items: type: string description: The prompt(s) to generate completions for example: Say this is a test max_tokens: type: integer description: The maximum number of tokens to generate default: 16 minimum: 1 example: 100 temperature: type: number description: Sampling temperature between 0 and 2 default: 1 minimum: 0 maximum: 2 example: 0.7 top_p: type: number description: Nucleus sampling parameter default: 1 minimum: 0 maximum: 1 example: 1 'n': type: integer description: Number of completions to generate default: 1 minimum: 1 maximum: 128 example: 1 stream: type: boolean description: Whether to stream back partial progress default: false example: false stop: oneOf: - type: string - type: array items: type: string maxItems: 4 description: Up to 4 sequences where the API will stop generating example: |+ presence_penalty: type: number description: Penalty for new tokens based on presence in text so far default: 0 minimum: -2 maximum: 2 example: 0 frequency_penalty: type: number description: Penalty for new tokens based on frequency in text so far default: 0 minimum: -2 maximum: 2 example: 0 CompletionResponse: type: object required: - id - object - created - model - choices properties: id: type: string description: Unique identifier for the completion example: cmpl-7QyqpwdfhqwajicIEznoc6Q47XAyW object: type: string enum: - text_completion description: Object type, always 'text_completion' created: type: integer description: Unix timestamp (in seconds) when the completion was created example: 1677664795 model: type: string description: The model used for completion example: llama-3.3-70b-versatile choices: type: array description: List of completion choices items: $ref: '#/components/schemas/CompletionChoice' usage: $ref: '#/components/schemas/Usage' Error: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string description: Human-readable error message example: Invalid API key provided type: type: string description: Error type example: invalid_request_error code: type: string description: Error code example: invalid_api_key CompletionChoice: type: object required: - text - index - finish_reason properties: text: type: string description: The generated text example: ' This is indeed a test' index: type: integer description: The index of this choice in the list example: 0 logprobs: type: object nullable: true description: Log probabilities of the output tokens finish_reason: type: string enum: - stop - length - content_filter description: Reason why the model stopped generating example: stop Usage: type: object required: - prompt_tokens - completion_tokens - total_tokens properties: prompt_tokens: type: integer description: Number of tokens in the prompt example: 20 completion_tokens: type: integer description: Number of tokens in the completion example: 10 total_tokens: type: integer description: Total number of tokens used example: 30 securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: >- Enter your Passy API key. Get your key from the Passy dashboard at https://dash.passy.ai/ ````