{"service":"Dellbot LLM API","protocol":"x402","facilitator":"CDP (api.cdp.coinbase.com/platform/v2/x402)","network":"Base mainnet (USDC)","pay_to":"0x234864Febc3AD18Fc99620c576729bdebfb62bCb","endpoint":"https://x402.dellbot.win","tiers":{"/chat-nano":{"price":"$0.001","models":["llama-3.3-70b"],"default_model":"llama-3.3-70b","description":"Cheapest LLM on CDP x402 Bazaar. OpenAI-compatible chat completion via Llama 3.3 70B (Venice AI). Supports tools/tool_choice for function calling and stream:true SSE passthrough."},"/chat":{"price":"$0.003","models":["deepseek-v3.2","grok-4-20-beta","qwen3-235b-a22b-instruct-2507","qwen3-235b-a22b-thinking-2507","venice-uncensored"],"default_model":"qwen3-235b-a22b-instruct-2507","description":"Mid-tier OpenAI-compatible chat completion. Choose from Qwen3 235B (instruct or thinking), DeepSeek V3.2, Grok 4 beta, or venice-uncensored. Supports tools/tool_choice and stream:true SSE."},"/chat-pro":{"price":"$0.01","models":["kimi-k2-thinking","qwen3-coder-480b-a35b-instruct-turbo"],"default_model":"kimi-k2-thinking","description":"Pro-tier reasoning & code. Kimi K2 Thinking for deep reasoning or Qwen3 Coder 480B for code generation. OpenAI-compatible. Supports tools/tool_choice and stream:true SSE."}},"usage":"POST to any tier with OpenAI-compatible body {messages, model?, max_tokens?, temperature?, tools?, tool_choice?, stream?}","streaming":"stream:true is accepted and SSE is passed through from Venice. CDP facilitator behavior with streaming responses is untested; payment is settled after the upstream response begins.","docs":"/docs"}