> ## Documentation Index > Fetch the complete documentation index at: https://docs.ninjachat.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a stateless response > OpenAI Responses-compatible text, vision, structured-output, and function-calling API. Set stream=true for typed lifecycle events. ## OpenAPI ````yaml /openapi.json post /responses openapi: 3.1.0 info: title: NinjaChat API version: 1.0.0 description: >- Clean-break NinjaChat v1. Chat and Responses bill actual token usage; images and videos use catalog unit pricing. servers: - url: https://www.ninjachat.ai/api/v1 security: [] paths: /responses: post: summary: Create a stateless response description: >- OpenAI Responses-compatible text, vision, structured-output, and function-calling API. Set stream=true for typed lifecycle events. parameters: - $ref: '#/components/parameters/IdempotencyKey' requestBody: content: application/json: schema: $ref: '#/components/schemas/ResponsesRequest' responses: '200': description: Completed response or SSE stream. content: application/json: schema: $ref: '#/components/schemas/ResponseObject' text/event-stream: schema: type: string '400': description: Invalid or unsupported request parameter. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '402': description: Insufficient balance or project spend limit reached. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Gateway error. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - bearerAuth: [] x-codeSamples: - lang: javascript label: TypeScript SDK source: >- import { NinjaChat } from "@ninjachat/sdk"; const client = new NinjaChat({ apiKey: process.env.NINJACHAT_API_KEY! }); const response = await client.responses.create({ model: "ninja/auto", input: "Explain the key tradeoffs in one paragraph.", }); console.log(response.output_text); - lang: python label: Python SDK source: |- import os from ninjachat import NinjaChat client = NinjaChat(api_key=os.environ["NINJACHAT_API_KEY"]) response = client.responses.create( model="ninja/auto", input="Explain the key tradeoffs in one paragraph.", ) print(response["output_text"]) components: parameters: IdempotencyKey: name: Idempotency-Key in: header required: false schema: type: string minLength: 1 maxLength: 255 description: >- Safely retry the same logical write without duplicate billing or execution. schemas: ResponsesRequest: type: object properties: model: type: string minLength: 1 maxLength: 160 models: type: array items: type: string minLength: 1 maxLength: 160 minItems: 1 maxItems: 15 input: anyOf: - type: string minLength: 1 - type: array items: anyOf: - type: object properties: type: type: string enum: - message role: type: string enum: - developer - system - user - assistant content: anyOf: - type: string minLength: 1 - type: array items: anyOf: - type: object properties: type: type: string enum: - input_text text: type: string minLength: 1 required: - type - text additionalProperties: false - type: object properties: type: type: string enum: - input_image image_url: type: string minLength: 1 maxLength: 7000000 detail: type: string enum: - auto - low - high required: - type - image_url additionalProperties: false - type: object properties: type: type: string enum: - input_file filename: type: string minLength: 1 maxLength: 255 file_data: type: string minLength: 1 maxLength: 7000000 file_url: type: string maxLength: 4096 format: uri media_type: type: string enum: - application/pdf - text/plain - text/markdown - text/csv - application/json required: - type additionalProperties: false minItems: 1 required: - role - content additionalProperties: false - type: object properties: type: type: string enum: - function_call call_id: type: string minLength: 1 maxLength: 128 name: type: string minLength: 1 maxLength: 64 arguments: type: string required: - type - call_id - name - arguments additionalProperties: false - type: object properties: type: type: string enum: - function_call_output call_id: type: string minLength: 1 maxLength: 128 output: anyOf: - type: string - type: array items: anyOf: - type: object properties: type: type: string enum: - input_text text: type: string minLength: 1 required: - type - text additionalProperties: false - type: object properties: type: type: string enum: - input_image image_url: type: string minLength: 1 maxLength: 7000000 detail: type: string enum: - auto - low - high required: - type - image_url additionalProperties: false - type: object properties: type: type: string enum: - input_file filename: type: string minLength: 1 maxLength: 255 file_data: type: string minLength: 1 maxLength: 7000000 file_url: type: string maxLength: 4096 format: uri media_type: type: string enum: - application/pdf - text/plain - text/markdown - text/csv - application/json required: - type additionalProperties: false minItems: 1 required: - type - call_id - output additionalProperties: false minItems: 1 instructions: type: string max_output_tokens: type: integer exclusiveMinimum: 0 maximum: 9007199254740991 description: >- Maximum completion tokens, including reasoning where the provider counts it. Must fit the selected provider's output and context limits. Defaults to 2048 when omitted. temperature: type: number minimum: 0 maximum: 2 top_p: type: number minimum: 0 maximum: 1 stream: type: boolean default: false store: type: boolean enum: - false default: false tools: type: array items: type: object properties: type: type: string enum: - function name: type: string minLength: 1 maxLength: 64 pattern: ^[a-zA-Z0-9_-]+$ description: type: string parameters: type: object additionalProperties: {} default: {} strict: type: boolean required: - type - name additionalProperties: false tool_choice: anyOf: - type: string enum: - none - auto - required - type: object properties: type: type: string enum: - function name: type: string minLength: 1 maxLength: 128 required: - type - name additionalProperties: false parallel_tool_calls: type: boolean text: type: object properties: format: oneOf: - type: object properties: type: type: string enum: - text required: - type additionalProperties: false - type: object properties: type: type: string enum: - json_object required: - type additionalProperties: false - type: object properties: type: type: string enum: - json_schema name: type: string minLength: 1 maxLength: 128 description: type: string schema: type: object additionalProperties: {} strict: type: boolean default: true required: - type - name - schema additionalProperties: false additionalProperties: false reasoning: $ref: '#/components/schemas/ChatReasoning' routing: $ref: '#/components/schemas/RoutingPolicy' metadata: type: object additionalProperties: type: string maxLength: 512 user: type: string maxLength: 256 required: - input additionalProperties: false ResponseObject: type: object properties: id: type: string object: type: string enum: - response created_at: type: integer status: type: string enum: - completed - incomplete error: type: 'null' incomplete_details: type: - object - 'null' properties: reason: type: string enum: - max_output_tokens - content_filter required: - reason additionalProperties: false instructions: type: - string - 'null' max_output_tokens: type: - integer - 'null' model: type: string minLength: 1 maxLength: 160 output: type: array items: anyOf: - type: object properties: id: type: string type: type: string enum: - reasoning status: type: string enum: - completed - incomplete summary: type: array items: type: object properties: type: type: string enum: - summary_text text: type: string required: - type - text additionalProperties: false required: - id - type - status - summary additionalProperties: false - type: object properties: id: type: string type: type: string enum: - message status: type: string enum: - completed - incomplete role: type: string enum: - assistant content: type: array items: type: object properties: type: type: string enum: - output_text text: type: string annotations: type: array items: {} required: - type - text - annotations additionalProperties: false required: - id - type - status - role - content additionalProperties: false - type: object properties: id: type: string type: type: string enum: - function_call status: type: string enum: - completed - incomplete call_id: type: string name: type: string arguments: type: string required: - id - type - status - call_id - name - arguments additionalProperties: false output_text: type: string parallel_tool_calls: type: boolean previous_response_id: type: 'null' store: type: boolean enum: - false usage: type: object properties: input_tokens: type: integer minimum: 0 input_tokens_details: type: object properties: cached_tokens: type: integer minimum: 0 cache_creation_tokens: type: integer minimum: 0 required: - cached_tokens - cache_creation_tokens additionalProperties: false output_tokens: type: integer minimum: 0 output_tokens_details: type: object properties: reasoning_tokens: type: integer minimum: 0 required: - reasoning_tokens additionalProperties: false total_tokens: type: integer minimum: 0 required: - input_tokens - input_tokens_details - output_tokens - output_tokens_details - total_tokens additionalProperties: false cost_usd: type: number minimum: 0 provider: type: - string - 'null' request_id: type: string routing: $ref: '#/components/schemas/RoutingSummary' metadata: type: object additionalProperties: type: string required: - id - object - created_at - status - error - incomplete_details - instructions - max_output_tokens - model - output - output_text - parallel_tool_calls - previous_response_id - store - usage - cost_usd - provider - request_id - routing - metadata additionalProperties: false ErrorResponse: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string param: type: - string - 'null' required: - message - type - code additionalProperties: false required: - error additionalProperties: false ChatReasoning: type: object properties: effort: type: string enum: - none - minimal - low - medium - high - xhigh max_tokens: type: integer minimum: 0 maximum: 9007199254740991 enabled: type: boolean additionalProperties: false RoutingPolicy: type: object properties: strategy: type: string enum: - balanced - cost - latency - quality providers: type: object properties: only: type: array items: type: string minLength: 1 maxLength: 128 minItems: 1 maxItems: 20 exclude: type: array items: type: string minLength: 1 maxLength: 128 minItems: 1 maxItems: 20 order: type: array items: type: string minLength: 1 maxLength: 128 minItems: 1 maxItems: 20 additionalProperties: false allow_fallbacks: type: boolean default: true require_parameters: type: boolean default: true data_policy: type: string enum: - default - no_training - zero_retention default: default caching: type: string enum: - auto max_cost_usd: type: number exclusiveMinimum: 0 maximum: 1000 additionalProperties: false RoutingSummary: type: object properties: strategy: type: string enum: - balanced - cost - latency - quality requested_models: type: array items: type: string minLength: 1 maxLength: 160 resolved_model: type: string minLength: 1 maxLength: 160 provider: type: - string - 'null' provider_attempts: type: array items: $ref: '#/components/schemas/ProviderAttemptReceipt' fallbacks_allowed: type: boolean data_policy: type: string enum: - default - no_training - zero_retention caching: type: string enum: - auto source: type: string enum: - request - project - default router: $ref: '#/components/schemas/RouterDecisionSummary' required: - strategy - requested_models - resolved_model - provider - fallbacks_allowed - data_policy additionalProperties: false ProviderAttemptReceipt: type: object properties: provider: type: string outcome: type: string enum: - served - failed_over - failed attempt_index: type: integer minimum: 0 required: - provider - outcome - attempt_index additionalProperties: false RouterDecisionSummary: type: object properties: id: type: string enum: - ninja/auto task: type: string classified_by: type: string enum: - regex - llm - llm-cached override: type: - string - 'null' enum: - long_context - multilingual reasoning: type: string candidates: type: array items: type: string minLength: 1 maxLength: 160 considered: type: array items: type: object properties: {} required: - id - task - classified_by - override - reasoning - candidates - considered additionalProperties: false securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: NinjaChat API key description: Use an API key created in the NinjaChat developer console. ````