- Do you train on my prompts?
- No. We forward your prompt only to the AI provider you select to generate the response. We don't store it beyond the request, and we don't share it with anyone else.
- What about "free" models?
- We don't ship free models that require sharing your data with the upstream provider. If a free tier's terms allow training on user prompts, we don't list it.
- How is this different from OpenRouter or Portkey?
- Pay-per-call USDC on Base or Solana via x402. No account, no API key, no subscription. Auto-fallback when a model is down. SDKs are OpenAI-compatible.
- Why USDC instead of a subscription?
- Agents can hold USDC; agents can't hold a credit card. Settlement happens on-chain in the same request via the x402 protocol — no prepaid credits, no minimum spend.
- What happens if a model is down?
- We auto-fallback to a comparable model and surface which one served you via the X-Fallback-Model response header, so your application never sees a hard failure.
- Are the SDKs OpenAI-compatible?
- Yes. Change base_url and you're done — every endpoint matches OpenAI's shape. @blockrun/llm for TypeScript, blockrun-llm for Python, both MIT-licensed.
- Can I use this in production?
- Yes. We run on Base mainnet with 1M+ calls per month. Use testnet.blockrun.ai for development against Base Sepolia.
- How does a payment actually happen?
- Your first request arrives unpaid and comes back as an HTTP 402 carrying a signed price quote for that specific call. Your client signs the quote with a wallet holding USDC and retries the request; the second request returns the completion and the payment settles on-chain. The SDKs perform this handshake for you, so in your code it is a single call.
- Do I need a wallet to start?
- For paid models, yes — you need a wallet holding USDC on Base or Solana, and that is the only credential involved. For free models you need nothing at all: no wallet, no payment header, no signup. Most people prototype against a free model first and fund a wallet once they are ready to move to a paid one.
- Which chains can I pay from?
- Base and Solana. Both settle in USDC, and the API surface is the same — pick whichever your wallet and treasury already live on. Each gateway publishes its own catalog and rates, so check the model you want on the chain you plan to pay from.
- Do streaming, tool calling, and vision work?
- Yes. Because the endpoint mirrors the OpenAI chat completions schema, stream: true, tool and function calling, multi-turn message histories, and image inputs all behave the way your existing OpenAI client already expects for models that support them.
- Am I charged when a request fails?
- No. Payment settles against a successful response, so an upstream error, a timeout, or a model that returns nothing is not billed. This is also why the on-chain record is a fair measure of real usage rather than of attempts.
- Are there rate limits?
- Free models are rate limited per IP address to keep them available to everyone. Paid requests are not rate limited — you have already paid for the call, so there is no reason to throttle it.
- How do I know what a call will cost before I make it?
- The 402 response quotes the exact price before you pay anything, so nothing is charged without an explicit signature from your wallet. Per-model rates are published on each model page and on the pricing page, and token-billed models charge only for the tokens a request actually consumes.