> ## Documentation Index > Fetch the complete documentation index at: https://docs.x402layer.cc/llms.txt > Use this file to discover all available pages before exploring further. # Create chat completion (pod adapter) > Runs ONE agent turn on your pod and returns an OpenAI `chat.completion`. Non-streaming only: `stream:true` is rejected with `400 stream_unsupported`. `usage` is always `null` (token counts are not faked in v1). Point any OpenAI SDK at `https://compute.x402layer.cc/pods/{id}/v1` with `model="agent-pod"`. Authenticate with a pod integration key as a bearer token: `Authorization: Bearer sk-sglpod-int-`. ## Drop-in with the OpenAI SDK The pod adapter is OpenAI-compatible. Point any OpenAI SDK at your pod's `/v1` base URL, use the pod integration key (`sk-sglpod-int-...`) as the API key, and call the model `agent-pod`. Each request runs one agent turn on your pod. Non-streaming only. Setting `stream: true` returns `400 stream_unsupported`. The response `usage` field is always `null` in v1. **Base URL:** `https://compute.x402layer.cc/pods/{id}/v1` ```python theme={null} from openai import OpenAI client = OpenAI( base_url="https://compute.x402layer.cc/pods/POD_ID/v1", api_key="sk-sglpod-int-...", # a pod integration key (POST /pods/{id}/api-keys) ) resp = client.chat.completions.create( model="agent-pod", messages=[{"role": "user", "content": "What can you do?"}], ) print(resp.choices[0].message.content) ``` ```ts theme={null} import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://compute.x402layer.cc/pods/POD_ID/v1", apiKey: process.env.POD_INTEGRATION_KEY, // sk-sglpod-int-... }); const r = await client.chat.completions.create({ model: "agent-pod", messages: [{ role: "user", content: "What can you do?" }], }); console.log(r.choices[0].message.content); ``` ## Quickstart (cURL) ```bash theme={null} curl https://compute.x402layer.cc/pods/POD_ID/v1/chat/completions \ -H "Authorization: Bearer sk-sglpod-int-..." \ -H "Content-Type: application/json" \ -d '{ "model": "agent-pod", "messages": [{"role": "user", "content": "What can you do?"}] }' ``` ## OpenAPI ````yaml POST /pods/{id}/v1/chat/completions openapi: 3.1.0 info: title: x402 Singularity Layer API description: >- OpenAPI-backed reference for marketplace discovery, payment routes, webhooks, wallet-first auth, agent endpoints, and ERC-8004 flows. version: 1.0.0 servers: - url: https://api.x402layer.cc security: [] tags: - name: Marketplace description: Public discovery and listing lookup - name: Public Endpoints description: Public endpoint metadata and hosted checkout context - name: Public Payment Links description: Hosted public payment-link lookup - name: Payments description: Hosted x402 payment challenge routes - name: Receipts description: Signed receipt lookup and verification helpers - name: Ratings description: Public listing ratings and authenticated rating actions - name: Webhooks description: Seller webhook management API - name: Agent Auth description: Wallet-first challenge and verification routes - name: Agent Endpoints description: Create, read, top up, and delete agent endpoints - name: ERC-8004 description: Agent registry and registration lifecycle routes - name: Marketplace Agents description: Public ERC-8004 marketplace discovery routes - name: Compute Catalog description: Compute plans, regions, and OS catalog - name: Compute Instances description: Provision, inspect, extend, and destroy compute instances - name: Compute API Keys description: API keys for compute agent access - name: Fundraiser Campaigns description: List, view, create, and edit fundraiser campaigns - name: Fundraiser Contributions description: Record and list campaign contributions - name: Fundraiser Comments description: Campaign comment threads - name: Fundraiser Media description: Campaign image uploads and OG images - name: Enterprise description: >- Enterprise partner configuration, endpoint listing, revenue stats, and transaction ledger - name: Staking description: Agentic $SGL staking - name: SGL Grid description: >- Decentralized, confidential, OpenAI-compatible inference served by attested TEE nodes. - name: Compute Credits description: Prepaid USDC credit balance shared across Machines and Grid. - name: Agent Pods description: >- Deploy and manage hosted agents (Agent Pods), plus the pod's OpenAI-compatible adapter for external clients. paths: /pods/{id}/v1/chat/completions: servers: - url: https://compute.x402layer.cc post: tags: - Agent Pods summary: Create chat completion (pod OpenAI adapter) description: >- Runs ONE agent turn on your pod and returns an OpenAI `chat.completion`. Non-streaming only: `stream:true` is rejected with `400 stream_unsupported`. `usage` is always `null` (token counts are not faked in v1). Point any OpenAI SDK at `https://compute.x402layer.cc/pods/{id}/v1` with `model="agent-pod"`. Authenticate with a pod integration key as a bearer token: `Authorization: Bearer sk-sglpod-int-`. parameters: - name: id in: path required: true schema: type: string format: uuid - name: Authorization in: header required: true schema: type: string example: Bearer sk-sglpod-int-... description: Pod integration key as a bearer token. requestBody: required: true content: application/json: schema: type: object required: - messages properties: model: type: string example: agent-pod description: Ignored by the adapter; use `agent-pod`. messages: type: array minItems: 1 items: type: object required: - role - content properties: role: type: string enum: - system - user - assistant content: type: string example: - role: user content: What can you do? stream: type: boolean default: false description: >- Must be false or omitted. `true` returns `400 stream_unsupported`. responses: '200': description: Chat completion content: application/json: schema: type: object properties: id: type: string example: chatcmpl_sgl_... object: type: string example: chat.completion created: type: integer model: type: string example: agent-pod choices: type: array items: type: object properties: index: type: integer message: type: object properties: role: type: string example: assistant content: type: string finish_reason: type: string example: stop usage: type: 'null' description: Always null in v1. '400': description: >- Invalid JSON, empty `messages`, or `stream:true` (`stream_unsupported`). '401': description: Missing or invalid integration key. '403': description: Pod expired (`pod_expired`). '404': description: Adapter not enabled, or pod unavailable (`pod_unavailable`). '413': description: Request body too large. '429': description: Daily request cap reached for this key (`daily_cap`). '502': description: Agent could not complete the request. '503': description: Agent is offline (`pod_offline`). '504': description: Agent took too long (`timeout`). ````