> ## Documentation Index > Fetch the complete documentation index at: https://apidocs.overtenai.com/llms.txt > Use this file to discover all available pages before exploring further. # Invoke an LLM > Non-streaming generation. The response body is the requested text or JSON value, without an envelope. The authenticated API key's organization pays; optional user_id/session_id provide attribution only. X-Request-ID, X-Credits-Used and X-LLM-Model response headers describe the call. ## OpenAPI ````yaml /openapi.json post /llm/invoke openapi: 3.1.0 info: title: Overten API version: 1.0.0 description: >- Generate and edit Word, Excel, and PowerPoint documents programmatically. Powered by the same agents as the Overten web app. contact: name: Overten Support url: https://overten.ai/support email: support@overten.ai license: name: Terms of Service url: https://overten.ai/terms servers: - url: https://backend.overtenai.com/api/v1 description: Production - url: http://localhost:8000/api/v1 description: Local development security: - ApiKeyAuth: [] paths: /llm/invoke: post: tags: - public - llm summary: Invoke an LLM description: >- Non-streaming generation. The response body is the requested text or JSON value, without an envelope. The authenticated API key's organization pays; optional user_id/session_id provide attribution only. X-Request-ID, X-Credits-Used and X-LLM-Model response headers describe the call. operationId: invoke_api_v1_llm_invoke_post requestBody: content: application/json: schema: $ref: '#/components/schemas/LLMInvokeRequest' examples: text: summary: Return text value: messages: - role: user content: Say hello. json: summary: Return JSON value: messages: - role: user content: Return the JSON array [1, 2, 3]. response_format: type: json json_schema: summary: Return a JSON object matching a schema value: messages: - role: user content: 'Classify this review: The service was excellent.' response_format: type: json_schema json_schema: type: object properties: sentiment: type: string enum: - positive - negative required: - sentiment additionalProperties: false required: true responses: '200': description: >- Consumer-defined output: text/plain for text, application/json for JSON modes. headers: X-Request-ID: schema: type: string X-Credits-Used: schema: type: integer X-LLM-Model: schema: type: string content: application/json: schema: {} examples: object: value: sentiment: positive array: value: - 1 - 2 - 3 text/plain: schema: type: string example: Hello. '401': description: Invalid API key '402': description: Insufficient organization API credits or exceeded LLM budget '403': description: Insufficient permissions '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: Rate limit exceeded '502': description: Model failure, invalid output or unavailable usage accounting '504': description: Model timeout security: - ApiKeyAuth: [] x-codeSamples: - lang: bash label: Return text source: >- curl -sS -w '\n' --request POST "https://backend.overtenai.com/api/v1/llm/invoke" \ -H "X-API-Key: $OVERTEN_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ { "role": "user", "content": "Say hello." } ] }' - lang: bash label: Return JSON source: >- curl -sS -w '\n' --request POST "https://backend.overtenai.com/api/v1/llm/invoke" \ -H "X-API-Key: $OVERTEN_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ { "role": "user", "content": "Return the JSON array [1, 2, 3]." } ], "response_format": { "type": "json" } }' | jq . - lang: bash label: Return a JSON object matching a schema source: >- curl -sS -w '\n' --request POST "https://backend.overtenai.com/api/v1/llm/invoke" \ -H "X-API-Key: $OVERTEN_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ { "role": "user", "content": "Classify this review: The service was excellent." } ], "response_format": { "type": "json_schema", "json_schema": { "type": "object", "properties": { "sentiment": { "type": "string", "enum": [ "positive", "negative" ] } }, "required": [ "sentiment" ], "additionalProperties": false } } }' | jq . components: schemas: LLMInvokeRequest: properties: messages: items: $ref: '#/components/schemas/LLMMessage' type: array minItems: 1 title: Messages response_format: $ref: '#/components/schemas/LLMResponseFormat' model: anyOf: - type: string - type: 'null' enum: - null - DeepSeek-V4-Pro - Kimi-K2.6 - auto - azure/gpt-5.4 - azure/gpt-5.4-mini - claude-opus-4-6 - claude-sonnet-4-6 - deepseek/deepseek-v4-flash-0731 - gemini-3.8-flash - qwen/qwen3.7-max - z-ai/glm-5.2 - z-ai/glm-5.3-flash title: Model description: >- Supported model ID, or auto for backend defaults. Fallback may use another configured model. user_id: anyOf: - type: string minLength: 1 - type: 'null' title: User Id description: Optional end-user attribution; the API key's organization pays. session_id: anyOf: - type: string minLength: 1 - type: 'null' title: Session Id description: >- Optional session for grouping usage. Does not restore conversation history. additionalProperties: false type: object required: - messages title: LLMInvokeRequest examples: - messages: - content: Say hello. role: user HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError LLMMessage: properties: role: type: string enum: - system - user - assistant title: Role content: type: string minLength: 1 title: Content additionalProperties: false type: object required: - role - content title: LLMMessage LLMResponseFormat: properties: type: type: string enum: - text - json - json_schema title: Type default: text json_schema: anyOf: - additionalProperties: true type: object - type: 'null' title: Json Schema description: >- JSON Schema (2020-12) for the returned value. Required for json_schema mode. additionalProperties: false type: object title: LLMResponseFormat ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: ApiKeyAuth: type: apiKey in: header name: X-API-Key description: >- Send `X-API-Key: sk_live_`. Keys are issued via POST /signup or via the dashboard. Legacy callers may also use `Authorization: Bearer sk_live_`. ````