> ## Documentation Index > Fetch the complete documentation index at: https://docs.aixy-gateway.com/llms.txt > Use this file to discover all available pages before exploring further. # Stream a Codex subscription response > Forward the official Codex client's native request to the fixed OpenAI Codex backend using its ChatGPT token. The separate personal Aixy key selects the authorized project and user. Supports HTTP SSE with supports_websockets=false in Codex configuration. Native history, tool identifiers, encrypted reasoning and streaming events are preserved. Activity records billing_channel=subscription, reported usage and no API cost. ChatGPT limits and credits still apply. This route provides no cross-provider translation, fallback or subscription pooling. ## OpenAPI ````yaml /openapi.json post /backend-api/codex/responses openapi: 3.1.0 info: title: Aixy Inference API version: 0.1.0 description: >- Route requests to configured AI providers through OpenAI- and Anthropic-compatible APIs. Aixy applies project access, model policies, guardrails, routing, budgets, and usage attribution before forwarding inference traffic. Create connections, API keys and policies in the Aixy dashboard. The management API is a dashboard service and is not a public integration contract. Native provider features depend on the selected model and connection; translated requests support the documented conversation and function-tool subset. Unsupported combinations return explicit errors. Examples use illustrative model IDs; select an ID available to your project. servers: - url: https://api.aixy-gateway.com description: Aixy production gateway security: [] tags: - name: OpenAI description: OpenAI-compatible conversations, function tools and incremental streams. - name: Anthropic description: Anthropic-compatible messages and provider-native input token counting. - name: Decisions description: Typed, non-streaming classification and scoring inference. - name: Models description: Discover the models available to your project API key. - name: Codex description: Use the official Codex client with each user's ChatGPT subscription. paths: /backend-api/codex/responses: post: tags: - Codex summary: Stream a Codex subscription response description: >- Forward the official Codex client's native request to the fixed OpenAI Codex backend using its ChatGPT token. The separate personal Aixy key selects the authorized project and user. Supports HTTP SSE with supports_websockets=false in Codex configuration. Native history, tool identifiers, encrypted reasoning and streaming events are preserved. Activity records billing_channel=subscription, reported usage and no API cost. ChatGPT limits and credits still apply. This route provides no cross-provider translation, fallback or subscription pooling. operationId: create_codex_subscription_response parameters: - $ref: '#/components/parameters/XRequestId' - $ref: '#/components/parameters/XAixySessionId' - name: ChatGPT-Account-ID in: header required: false schema: type: string description: >- Account/workspace selected by Codex; preserved for OpenAI validation. It does not select or authorize an Aixy tenant. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CodexResponsesRequest' example: model: native-model-id input: - role: user content: - type: input_text text: Hello stream: true store: false responses: '200': description: >- Incremental native SSE. A successful stream ends with response.completed; errors can occur after headers or text arrive. headers: x-request-id: description: >- Aixy request identifier for correlation with Activity and support. schema: type: string example: req_example_01 openai-model: schema: type: string description: Effective upstream model, when reported. X-Models-Etag: schema: type: string description: Catalog revision observed by Codex. x-codex-turn-state: schema: type: string description: Opaque routing state for the same turn. x-codex-primary-used-percent: schema: type: string description: Used share of the provider's primary quota window. x-codex-secondary-used-percent: schema: type: string description: Used share of the provider's secondary quota window. content: text/event-stream: schema: type: string example: >+ event: response.created data: {"type":"response.created","response":{"id":"resp_example"}} event: response.output_text.delta data: {"type":"response.output_text.delta","delta":"Hello"} event: response.completed data: {"type":"response.completed","response":{"id":"resp_example","usage":{"input_tokens":10,"output_tokens":1,"total_tokens":11}}} '400': $ref: '#/components/responses/GatewayError' '401': $ref: '#/components/responses/GatewayError' '403': $ref: '#/components/responses/GatewayError' '404': $ref: '#/components/responses/GatewayError' '408': $ref: '#/components/responses/GatewayError' '413': $ref: '#/components/responses/GatewayError' '429': $ref: '#/components/responses/GatewayError' '502': $ref: '#/components/responses/GatewayError' '503': $ref: '#/components/responses/GatewayError' '504': $ref: '#/components/responses/GatewayError' default: $ref: '#/components/responses/NativeProviderError' security: - CodexGatewayKey: [] CodexChatGPTToken: [] components: parameters: XRequestId: name: X-Request-ID in: header required: false description: Optional caller-generated request identifier for end-to-end tracing. schema: type: string maxLength: 255 XAixySessionId: name: X-Aixy-Session-ID in: header required: false description: >- Optional opaque conversation identifier recorded in Activity metadata. Reuse it for every call in a conversation. Sessions are isolated by organization, project, user and API key. Use no personal data or secrets. Invalid values are ignored. The header is not forwarded, grants no permissions and does not change routing affinity. schema: type: string minLength: 1 maxLength: 128 pattern: ^[A-Za-z0-9._:-]+$ example: conversation-82 schemas: CodexResponsesRequest: type: object required: - model - input - stream - store properties: model: type: string description: Native Codex model slug, without an Aixy provider prefix. input: type: array items: type: object additionalProperties: true description: Native conversation history, tool items and opaque reasoning state. stream: type: boolean const: true store: type: boolean const: false additionalProperties: true InferenceErrorResponse: type: object required: - error properties: error: type: object required: - message properties: message: type: string code: type: - string - 'null' type: type: - string - 'null' param: type: - string - integer - 'null' details: type: - object - 'null' additionalProperties: true additionalProperties: true type: type: string request_id: type: string additionalProperties: true responses: GatewayError: description: >- The gateway or upstream provider rejected the request. Gateway codes identify invalid_request or unsupported_feature (400), invalid_gateway_api_key (401), access or policy denials (403), unavailable models (404), request deadlines (408/504), body limits (413), hard-budget admission failures (424), and upstream or gateway availability failures (502/503). Native provider error details may differ. headers: x-request-id: description: Aixy request identifier for correlation with Activity and support. schema: type: string example: req_example_01 content: application/json: schema: $ref: '#/components/schemas/InferenceErrorResponse' example: error: code: invalid_gateway_api_key message: Gateway API key is invalid or revoked NativeProviderError: description: >- A native provider may return another error status and its original payload. After streaming starts, failures can arrive inside the SSE stream instead of changing the HTTP status. Handle both HTTP errors and protocol error events. headers: x-request-id: description: Aixy request identifier for correlation with Activity and support. schema: type: string example: req_example_01 content: application/json: schema: type: object additionalProperties: true securitySchemes: CodexGatewayKey: type: apiKey in: header name: X-Gateway-Key description: >- The caller's personal, project-scoped Aixy key. Aixy validates and removes this header before forwarding. It does not replace the ChatGPT token. CodexChatGPTToken: type: http scheme: bearer description: >- The user's ChatGPT access token supplied by the official Codex client. Forwarded only to the fixed Codex backend; never stored as a connection. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.