Documentation
Build with Onchain Router
Choose an integration for text, images, and speech, with clear publication status and human-owned payment setup.
Onchain Router gives your agents one provider-neutral API for text, images, text to speech, and speech to text. Pay per successful request with USDC on Base and receive a durable receipt. You do not need payer registration or a provider API key.
Start here
- Make your first request: follow the quickstart, from installation and wallet funding to a response and receipt.
- Try a browser interface: use the Workbench guide for wallet connection, preview, payment, and recovery.
- Connect an existing agent: choose OpenClaw, Hermes Agent, or MCP.
- Build an integration: start with the direct API guide and endpoint reference.
A standard OpenAI client alone cannot pay the public API. Use an x402-capable transport or our local proxy. Buyer Runtime handles wallets, spending policies, payments, recovery, and receipts for our local tools; it is not a separate model endpoint.
Integration reference
| Integration | Best for | Availability | Source |
|---|---|---|---|
| Direct API | You already have an x402 buyer | Public API | Use the public API |
| TypeScript SDK | You are building a Node.js application | npm stable · 0.2.0 | GitHub |
| Buyer CLI | You work in a terminal | npm stable · 0.2.0 | GitHub |
| MCP | Your agent uses native tools | npm stable · 0.2.0 | GitHub |
| Local OpenAI proxy | Your app accepts an OpenAI base URL | npm stable · 0.2.0 | GitHub |
| Agent Skill | Your coding agent follows reusable instructions | MIT source · stable 0.2.0 | GitHub |
| OpenClaw | You use OpenClaw agents | GitHub stable · 0.2.1 | GitHub |
| Hermes Agent | You use Hermes Agent | GitHub stable · 0.2.0 | GitHub |
Read how the runtime works for the shared wallet and payment lifecycle.
Before a paid request
Check that your buyer supports x402 v2 exact with USDC on Base. Use a dedicated low-balance wallet, review the exact request price before signing, and keep the result and receipt together. Follow the first-request guide for the complete flow.
For our client tools, review installation and availability, then install the exact npm or host-native GitHub version listed there. OpenClaw and Hermes Agent have dedicated copyable install guides. For a browser walkthrough, see Workbench.
Choose a capability
- Text: Chat Completions or Anthropic-style Messages.
- Images: one generated image with a hosted URL or Base64 output.
- Text to speech: hosted MP3 audio with a curated voice.
- Speech to text: an MP3 transcript, with provider-retention disclosure.
The current catalog determines which models and parameters work. The brand stays provider-neutral; supporting a request format does not imply support for that provider's models. Video is not currently available.
Source of truth
These guides are maintained in OnchainRouter/docs. The website, search and agent-readable Markdown use the same reviewed documentation snapshot. See model selection and routing for the distinction between public features and unpublished automatic-routing work. Venice text models are available through explicit model IDs.
Use live models, live pricing, and OpenAPI. The HTTP 402 challenge determines the exact request price; the receipt confirms payment and normalized usage. See pricing for the 0% service fee launch promotion and the separate fixed fee.
For agents, llms.txt is the compact index and llms-full.txt is the complete Markdown documentation. products.json records publication and build availability, not live uptime.