> ## Documentation Index > Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request. > Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance. > For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code. > The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust. > Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool. > Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md. # Get a generation > Retrieve a specific generation by ID. Fetches the stored audit record for a given `request_id` that belongs to your team. New requests receive a server-generated `G-` generation ID, returned in the `x-request-id` response header and generation response. Use that ID for request logs, generation lookup, and support. A caller-supplied `x-request-id` does not replace the generation ID. Existing UUID-based log IDs remain valid for lookup. Use: * `GET /v1/generations?id=` When the gateway captured full request details for that generation, the response also includes: * `replay_supported`: whether a replay-ready payload is available * `replay_request`: the stored request body you can send back to the original endpoint for a controlled rerun Typical replay flow: 1. Read the generation record with `GET /v1/generations?id=`. 2. Check `replay_supported === true`. 3. Re-submit `replay_request` to the original endpoint named by `endpoint` such as `/v1/chat/completions` or `/v1/responses`. ## OpenAPI ````yaml openapi/v1/openapi.yaml GET /generations openapi: 3.0.3 info: title: Phaseo Gateway API description: >- A gateway API for accessing various AI models with OpenAI-compatible endpoints. version: 1.0.0 contact: name: Phaseo url: https://phaseo.app email: danielbutler500@gmail.com servers: - url: https://api.phaseo.app/v1 description: Global routing security: - BearerAuth: [] tags: - name: Gateway description: Core Phaseo Gateway operations. paths: /generations: get: tags: - Gateway summary: Get generation description: Retrieve a specific generation by ID. operationId: getGeneration parameters: - name: id in: query required: true description: >- Public generation ID returned by inference, in G- format. Historical identifiers, including UUIDs, are also accepted. schema: type: string responses: '200': description: Generation data content: application/json: schema: $ref: '#/components/schemas/GenerationResponse' '401': description: Unauthorized content: application/json: schema: type: object properties: ok: type: boolean error: type: string reason: type: string '404': description: Not found content: application/json: schema: type: object properties: ok: type: boolean error: type: string components: schemas: GenerationResponse: type: object properties: created_at: type: string format: date-time request_id: type: string description: >- Public generation identifier. New generations use G- format; historical logs may contain earlier identifiers, including UUIDs. team_id: type: string app_id: type: string nullable: true endpoint: type: string model_id: type: string provider: type: string native_response_id: type: string nullable: true stream: type: boolean byok: type: boolean status_code: type: number success: type: boolean error_code: type: string nullable: true error_message: type: string nullable: true latency_ms: type: number generation_ms: type: number usage: type: object nullable: true properties: prompt_tokens: type: number completion_tokens: type: number total_tokens: type: number cost_nanos: type: number currency: type: string pricing_lines: type: array items: type: object key_id: type: string throughput: type: number nullable: true replay_supported: type: boolean description: >- Whether a replay-ready request payload is available for this generation. replay_request: type: object nullable: true additionalProperties: true description: >- Replay-ready request payload captured for this generation when available. securitySchemes: BearerAuth: type: http scheme: bearer description: Bearer token authentication ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.