> ## Documentation Index > Fetch the complete documentation index at: https://predev.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Agents: start with https://docs.pre.dev/agents.md, which has complete recipes, plan access, polling rules, errors and limits. > Authenticate with the workspace API key (pdk_…) from Integrations → Built-in, sent as Authorization: Bearer . > REST API: https://api.pre.dev (OpenAPI: https://docs.pre.dev/api-reference/openapi.json). AI Gateway: https://api.pre.dev/v1, OpenAI-compatible (OpenAPI: https://docs.pre.dev/api-reference/ai-gateway.openapi.json). > pre.dev MCP server: npx -y @predotdev/mcp setup adds it to every local coding agent with every pre.dev tool plus the user's own Chrome; the hosted server is https://api.pre.dev/mcp. Search these docs over MCP at https://docs.pre.dev/mcp. # API overview > The public REST API for specifications, browser automation, AI model calls, and credit balances. | Interface | Base URL | | - | - | | REST: specifications, browser tasks, and credits | `https://api.pre.dev` | | AI Gateway | `https://api.pre.dev/v1` | | Hosted MCP server | `https://api.pre.dev/mcp` | REST paths are mounted at the root: use `/browser-agent`, not `/api/v1/browser-agents`. The AI Gateway is the one API under a prefix, `/v1`. Copy your pre.dev API key from **Integrations → Built-in** in the dashboard: [pre.dev/projects/integrations](https://pre.dev/projects/integrations?tab=built-in) for your personal workspace, or the Integrations page of a team workspace. Workspace keys start with `pdk_`. | Interface | Send the key as | | - | - | | REST and AI Gateway | `Authorization: Bearer ` (recommended) or `x-api-key: ` | | MCP server | Browser sign-in (OAuth) in interactive clients, or `Authorization: Bearer `, `x-api-key`, or `predev-api-key` | Read [authentication](https://predev.mintlify.site/api-reference/authentication.md) and [errors](https://predev.mintlify.site/api-reference/errors.md) before building an integration. ## Specifications | Method | Path | Reference | | - | - | - | | POST | `/fast-spec` | [Generate a Fast Spec](https://predev.mintlify.site/architect-agent/api/fast-spec.md) | | POST | `/deep-spec` | [Generate a Deep Spec](https://predev.mintlify.site/architect-agent/api/deep-spec.md) | | GET | `/spec-status/{specId}` | [Status and full artifacts](https://predev.mintlify.site/architect-agent/api/spec-status.md) | | GET | `/get-plan` | [A project's verified plan](https://predev.mintlify.site/architect-agent/api/get-plan.md) | | GET | `/list-specs` | [List specifications](https://predev.mintlify.site/architect-agent/api/list-specs.md) | | GET | `/find-specs` | [Search specifications](https://predev.mintlify.site/architect-agent/api/find-specs.md) | | GET | `/credits-balance` | [Credit balance](https://predev.mintlify.site/architect-agent/api/credits-balance.md) | ## Browser Agents | Method | Path | Reference | | - | - | - | | POST | `/browser-agent` | [Submit tasks](https://predev.mintlify.site/browser-agents/api/run-task.md) | | GET | `/browser-agent/{id}` | [Status and results](https://predev.mintlify.site/browser-agents/api/task-status.md) | | GET | `/browser-agent/{id}/stream` | [Watch an existing run with SSE](https://predev.mintlify.site/browser-agents/api/stream-task.md) | | GET | `/browser-agent/{id}/ws` | [Get a live browser WebSocket URL](https://predev.mintlify.site/browser-agents/api/live-browser.md) | | GET | `/list-browser-agents` | [List runs](https://predev.mintlify.site/browser-agents/api/list-tasks.md) | | GET | `/browser-agent-status` | [Your queue and in-flight limit](https://predev.mintlify.site/browser-agents/api/queue-status.md) | | GET | `/browser-agent-capacity` | [Service capacity](https://predev.mintlify.site/browser-agents/api/capacity.md) | ## AI Gateway The [AI Gateway](https://predev.mintlify.site/ai-gateway/overview.md) is an OpenAI-compatible API for hundreds of models from every major lab, with the same key and credits. It covers chat completions, the Anthropic Messages shape, embeddings, images, video, audio, files, and a model catalog with credit prices. Point the stock OpenAI, Vercel AI, or Anthropic SDK at that base URL; see the [quickstart](https://predev.mintlify.site/ai-gateway/quickstart.md) and [pricing](https://predev.mintlify.site/coding-agent/plans-and-credits.md#ai-gateway-calls). ## Long-running jobs Specifications, browser runs, and video generation run as jobs. All three follow one pattern: submit the job, save the ID it returns, poll or stream that ID, and read the result once the status is terminal. ![The async job pattern in four steps for specs, browser runs, and video jobs: submit the job, save the ID it returns, poll or stream it, and stop at a terminal status to read the result.](https://mintcdn.com/predev/7eUhmIdZncrpx3fC/images/diagrams/async-jobs-light.svg?fit=max\&auto=format\&n=7eUhmIdZncrpx3fC\&q=85\&s=0757fee9f8466faff454904d8458ccb6) | Job | Submit | Save | Poll or stream | Terminal status | | - | - | - | - | - | | Specification | `POST /fast-spec` or `/deep-spec` with `async: true` | `specId` | `GET /spec-status/{specId}` | `completed` returns the Markdown, JSON, and available graphs; `failed` returns `errorMessage` | | Browser run | `POST /browser-agent` with `async: true` | `id` | `GET /browser-agent/{id}`, or stream `GET /browser-agent/{id}/stream` | `completed` or `failed`; read each task's `status` before its data | | Video | `POST /v1/videos` | `id` | `GET /v1/videos/{jobId}` | `completed`, then download `GET /v1/videos/{jobId}/content`; or `failed` | ## SDKs and MCP The [Node SDK](https://predev.mintlify.site/architect-agent/sdks/node.md) and [Python SDK](https://predev.mintlify.site/architect-agent/sdks/python.md) wrap specification and browser operations. Use direct HTTP for endpoints or headers without a wrapper, including live browser URLs, existing-run SSE, and browser idempotency keys. The [MCP server](https://predev.mintlify.site/architect-agent/mcp-setup.md) exposes eight primary tools and three deprecated browser aliases. MCP uses JSON-RPC over HTTP; its parameter names and result envelopes differ from REST. See the [tool reference](https://predev.mintlify.site/mcp/tools.md). Two OpenAPI 3.1 files describe the public API, for code generation or agent ingestion: [openapi.json](https://predev.mintlify.site/api-reference/openapi.json) covers specifications, browser tasks, and the credit balance, and [ai-gateway.openapi.json](https://predev.mintlify.site/api-reference/ai-gateway.openapi.json) covers every AI Gateway `/v1` operation. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.