{"uid":"cap_cpP_uH14pjaQX-Cy3Wiz3","slug":"x402-llm-gateway-erb-llm-0bf3148f","name":"x402 LLM Gateway (erb-llm)","description":"OpenAI-compatible chat completions served by a self-hosted 27B open-weight LLM. Pay per call in USDC on Base via x402 - no API key or account. Use it for text generation, summarization, classification and agent tool calls that need cheap, private inference. Send a messages array (plus optional model, max_tokens, temperature); receive standard OpenAI chat.completion JSON. A free trial (POST /v1/trial) is open during promo windows.","url":"https://api.erb-llm.com/v1/chat/completions","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"Model ID from the free GET /v1/models endpoint (e.g. qwen/qwen3.8-27b). Optional - a default chat model is chosen if omitted."},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"minItems":1,"description":"OpenAI chat messages (system/user/assistant)."},"max_tokens":{"type":"integer","minimum":1,"description":"Optional output token ceiling. This tier caps output at 4096 tokens - higher values are clamped to 4096, not rejected. Use the long/extended tiers for bigger outputs."},"temperature":{"type":"number","maximum":2,"minimum":0}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_-5ygho5CFb9uX_xj1uqtg","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Serves OpenAI-compatible chat completions via a self-hosted 27B open-weight LLM, billed at $0.005 USDC per call over x402 with no API key required.","exampleAgentPrompt":"Summarize the following meeting notes into 3 bullet points using the open-weight LLM — pay the per-call USDC fee automatically: 'Q3 planning meeting covered budget cuts, new product timeline, and hiring freeze.'","exampleUseCases":[{"title":"Cheap private text summarization","prompt":"Summarize this 2,000-word legal contract into the 5 most important points — use the self-hosted open-weight model so it stays private and I'll pay per call in USDC."},{"title":"Agent tool call with open-weight model","prompt":"My agent needs to classify incoming customer support tickets as 'billing', 'technical', or 'other' — route them through the erb-llm 27B model and keep max_tokens at 50 so it stays fast and cheap."},{"title":"Anonymous LLM completion without signup","prompt":"Write me a short product description for a noise-cancelling headphone called SoundZen — use temperature 0.7, up to 200 tokens, and don't require me to create an account anywhere."}],"resultDescription":"A standard OpenAI chat.completion JSON object containing an 'id', 'object', 'created', 'model', 'choices' array (each with a 'message' object holding 'role' and 'content', plus a 'finish_reason'), and a 'usage' object showing prompt_tokens, completion_tokens, and total_tokens.","failureModes":["Payment not included or insufficient USDC balance triggers a 402 Payment Required response","Invalid or missing messages array returns a 400 validation error","Requested model ID not available returns an error — check GET /v1/models for valid IDs","Temperature out of range (0–2) or max_tokens below 1 causes validation failure","Service unavailability or model overload may return 503 or timeout"],"whenToPreferThis":"Choose this endpoint when you need cheap, pay-per-call LLM inference with no API key, no account registration, and no subscription — especially for agents that handle crypto (USDC on Base) natively via x402. It is ideal for privacy-sensitive workloads on a self-hosted open-weight model, or when you want OpenAI-compatible chat completions without being locked into OpenAI or Anthropic pricing tiers. Prefer alternatives like OpenAI or Anthropic if you need the very latest frontier models, guaranteed SLAs, or fine-tuned proprietary capabilities.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:41:52.129Z","isFirstParty":false}