> ## Documentation Index > Fetch the complete documentation index at: https://docs.nuwacom.ai/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI Chat Completion > Create a new AI completion. You can find the supported models using [List all AI models](/api-reference/ai/list-all-ai-models). ## OpenAPI ````yaml /openapi.yaml post /api/v1/openai/chat/completions openapi: 3.1.0 info: title: Nuwacom API description: API for Nuwacom application version: 1.0.0 servers: - url: https://{customer-tenant}.nuwacom.ai description: Nuwacom API security: - bearerAuth: [] paths: /api/v1/openai/chat/completions: post: tags: - Completion API summary: OpenAI Chat Completion description: >- Create a new AI completion. You can find the supported models using [List all AI models](/api-reference/ai/list-all-ai-models). operationId: postApiV1OpenaiChatCompletions parameters: - in: header name: x-space-id schema: type: string required: false description: >- Space ID to run the completion in. Used as a fallback when `space_id` is not set in the request body. requestBody: content: application/json: schema: type: object properties: model: anyOf: - type: string nullable: true description: >- Use this in the API call to specify the model to use for the completion request. Is generally the model ID from the LLM provider (e.g., "gpt-4o", "o1"). imageGenerationModel: enum: - gemini-2.5-flash-image - gemini-3-pro-image - gemini-3.1-flash-image - gemini-3.1-flash-image-eu - imagen - imagen-fast - gpt-image-2 - gpt-image-2.5-sunburst - flux-1-1-pro-ultra - flux-1-kontext-pro - flux-2-pro - gemini-3-pro-image-preview - gemini-3.1-flash-image-preview description: >- User-selected image generation model id. Overrides the workspace default when present. Validated server-side against the AI_ENABLED_IMAGE_MODELS feature flag. temperature: type: number description: >- Sampling temperature. Higher values make responses more adventurous; lower values keep them conservative. top_p: type: number description: >- Nucleus sampling parameter. Use this instead of temperature when you want to strictly cap how much of the probability mass is considered. agentId: anyOf: - type: string format: uuid nullable: true description: >- Unique ID of the agent to use for the completion request. Used to load the agent's full configuration (system prompt, knowledge sources, etc.). NB: Agent must already be created in the database and available for the space. agentPublished: type: boolean description: >- Which version of the agent to use: true (default) = published version, false = draft. Useful to test an agent that has not been published yet. voiceId: anyOf: - type: string format: uuid nullable: true description: >- UUID of the Voice to use for the completion request. NB: Voice must already be created in the database and available for the space. taskId: anyOf: - type: string format: uuid nullable: true description: >- ID of the Task to use for the completion request. Used to tie the completion back to a workflow step or scheduled job. NB: Task must already be created in the database and available for the space. capabilities: type: object properties: webSearch: type: boolean knowledgeBaseSearch: type: boolean visionEnabled: type: boolean canvasEnabled: type: boolean required: [] description: >- Provide an object of capabilities to enable the LLM perform specific tasks better (e.g., web search, internal KB, canvas, etc.). attachmentIds: type: array items: type: string format: uuid description: >- Array of asset IDs (files, snippets, etc.) that should be injected into the completion request as supporting context. contentIds: type: array items: type: string format: uuid description: >- Array of Content document IDs to include in the RAG context. Used to pass relevant document IDs so their content is included as additional background information for the completion request. folderIds: type: array items: type: string format: uuid description: >- Array of Folder IDs to include in the RAG context. When provided, the LLM will use assets/documents within these folders as additional background information for the completion request. toolOptions: type: object properties: language: type: string audience: enum: - c_level - leaders_managers - new_customers_prospects - existing_customers - internal_team_members - partners_vendors imageStyle: enum: - photorealistic - illustration - sketch - comic colorMood: enum: - vibrant - warm - cool - monochrome - pastel documentTemplate: enum: - report - article - briefing - social_media_post - strategy_paper - speech templateId: type: string videoStyle: enum: - realistic - cinematic - motion_graphics - animated aspectRatio: enum: - horizontal - vertical sourceFilters: type: object properties: docs: type: boolean notes: type: boolean required: [] required: [] description: >- User preferences for AI behavior including language, audience, and image generation style. These options are injected into the system prompt. toolGroups: type: array items: anyOf: - type: object properties: kind: enum: - nuwacom tools: type: array items: type: string minItems: 1 required: - kind - tools - type: object properties: kind: enum: - paragon integrationType: type: string integrationId: anyOf: - type: string format: uuid nullable: true tools: type: array items: type: string minItems: 1 required: - kind - integrationType - tools - type: object properties: kind: enum: - mcp mcpClientId: type: string format: uuid integrationId: anyOf: - type: string format: uuid nullable: true tools: type: array items: type: string minItems: 1 required: - kind - mcpClientId - tools description: >- Grouped tool configurations keyed by provider context (nuwacom, paragon integration type, or MCP client). Backend expands these groups into per-tool configs. skillIds: type: array items: type: string format: uuid description: >- Skill IDs explicitly selected by the user from the skills dropdown. When present without an agent, only these skills are loaded. workflowContext: type: object properties: enabled: type: boolean isWorkflowBuilder: type: boolean workflow_intent: enum: - create - update current_workflow: type: object properties: nodes: type: array items: type: object properties: id: type: string type: type: string position: type: object properties: x: type: number 'y': type: number required: - x - 'y' data: type: object properties: label: type: string type: type: string category: type: string config: type: object additionalProperties: $ref: '#/components/schemas/InlinedDef0_0' required: - label - type - category - config required: - id - position - data edges: type: array items: type: object properties: id: type: string source: type: string target: type: string sourceHandle: anyOf: - type: string nullable: true targetHandle: anyOf: - type: string nullable: true required: - id - source - target required: - nodes - edges connected_integrations: type: array items: type: object properties: type: type: string name: type: string credentialId: anyOf: - type: string nullable: true required: - type - name canvas_workflow_id: type: string required: - enabled messages: type: array items: type: object properties: id: type: number role: enum: - assistant - user - system content: anyOf: - type: string - type: array items: anyOf: - type: object properties: type: enum: - text text: type: string required: - type - text - type: object properties: type: enum: - image kbAssetId: type: string format: uuid required: - type - kbAssetId - type: object properties: type: enum: - file_data data: type: string mediaType: type: string fileName: type: string required: - type - data - mediaType - fileName required: - role - content minItems: 1 description: >- Ordered chat messages that make up the conversation history. Always include the user’s latest turn; prepend prior turns when you want additional context. stream: type: boolean description: >- When true the API sends partial chunks as the model generates them (ideal for typing indicators). Set to false to receive a single response payload. parent_message_id: anyOf: - type: number nullable: true description: >- Internal reference to the last assistant message in the thread. Include this when you need the completion to “continue” an earlier answer. conversation_id: anyOf: - type: string format: uuid nullable: true description: >- Conversation UUID tying multiple completions together. Provide it to append to an existing thread; leave empty to start fresh. space_id: anyOf: - anyOf: - type: string minLength: 2 maxLength: 6 - type: string minLength: 21 maxLength: 21 - type: array items: anyOf: - type: string minLength: 2 maxLength: 6 - type: string minLength: 21 maxLength: 21 minItems: 1 description: >- Unique identifier of the space the completion should be run in. required: - messages - space_id responses: '200': description: >- Successful completion response (see [OpenAI Completions Object](https://platform.openai.com/docs/api-reference/completions/object)) externalDocs: description: OpenAI API documentation for chat completions url: https://platform.openai.com/docs/api-reference/chat/create components: schemas: InlinedDef0_0: anyOf: - type: string - type: number - type: boolean - type: 'null' - type: array items: $ref: '#/components/schemas/InlinedDef0_0' - type: object additionalProperties: $ref: '#/components/schemas/InlinedDef0_0' securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.