{"x402Version":2,"payTo":"0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8","resources":[{"id":35603,"slug":"35603","resource":"https://api.erb-llm.com/v1/chat/completions","description":"Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer questions. Send a messages array, get chat.completion JSON. Pay per call in USDC on Base (x402), no API key or account. Tiers by output cap: quick 4,096 / long 8,192 / extended 32,768 tokens. Free trial: POST /v1/trial.","type":"http","serviceName":"Private LLM Inference","resourceType":"AI Inference","x402Version":2,"accepts":[{"scheme":"exact","network":"eip155:8453","payTo":"0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8","asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","amount":"1000","amountUsd":0.001,"maxTimeoutSeconds":300}],"outputSchema":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"},"extensions":{"bazaar":{"info":{"input":{"body":{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"hello","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":1,"prompt_tokens":30,"total_tokens":31},"x402":{"charged":"$0.001","inference_ms":1830,"output_cap":4096,"tier":"quick","tokens_out":1}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"max_tokens":{"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.","minimum":1,"type":"integer"},"messages":{"description":"OpenAI chat messages (system/user/assistant).","items":{"properties":{"content":{"type":"string"},"role":{"enum":["system","user","assistant"],"type":"string"}},"required":["role","content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.","type":"string"},"temperature":{"maximum":2,"minimum":0,"type":"number"}},"required":["messages"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}},"tags":["llm","chat","inference","private","openai-compatible","bazaar"],"sourceHost":"api.erb-llm.com","lastUpdated":"2026-10-11T15:41:35.033Z","quality":{"calls30d":20,"uniquePayers30d":4,"lastCalledAt":"2026-10-11T15:41:34.617Z"},"metadata":{"serviceName":"Private LLM Inference","extensions":{"bazaar":{"info":{"input":{"body":{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"hello","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":1,"prompt_tokens":30,"total_tokens":31},"x402":{"charged":"$0.001","inference_ms":1830,"output_cap":4096,"tier":"quick","tokens_out":1}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"max_tokens":{"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.","minimum":1,"type":"integer"},"messages":{"description":"OpenAI chat messages (system/user/assistant).","items":{"properties":{"content":{"type":"string"},"role":{"enum":["system","user","assistant"],"type":"string"}},"required":["role","content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.","type":"string"},"temperature":{"maximum":2,"minimum":0,"type":"number"}},"required":["messages"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}}},"liveness":{"reliability":null},"verified":false,"featured":false},{"id":35599,"slug":"35599","resource":"https://api.erb-llm.com/v1/long","description":"Privacy-first long-form inference: 8,192-token output cap on a local open-weight model on dedicated hardware - prompts never reach OpenAI/Anthropic or any third-party cloud. OpenAI-compatible chat completions (messages array in, chat.completion JSON out) for summarization, drafting, extraction, translation, code, multi-paragraph answers. Pay per call in USDC on Base (x402), no API key or account. Shorter work? Use the cheaper quick tier (4,096 tokens).","type":"http","serviceName":"Private LLM Inference - Long","resourceType":"AI Inference","x402Version":2,"accepts":[{"scheme":"exact","network":"eip155:8453","payTo":"0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8","asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","amount":"10000","amountUsd":0.01,"maxTimeoutSeconds":300}],"outputSchema":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"},"extensions":{"bazaar":{"info":{"input":{"body":{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"hello","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":1,"prompt_tokens":30,"total_tokens":31},"x402":{"charged":"$0.01","inference_ms":1830,"output_cap":8192,"tier":"long","tokens_out":1}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"max_tokens":{"description":"Optional output token ceiling. This tier caps output at 8192 tokens - higher values are clamped to 8192, not rejected. Use the long/extended tiers for bigger outputs.","minimum":1,"type":"integer"},"messages":{"description":"OpenAI chat messages (system/user/assistant).","items":{"properties":{"content":{"type":"string"},"role":{"enum":["system","user","assistant"],"type":"string"}},"required":["role","content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.","type":"string"},"temperature":{"maximum":2,"minimum":0,"type":"number"}},"required":["messages"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}},"tags":["llm","longform","inference","private","openai-compatible","bazaar"],"sourceHost":"api.erb-llm.com","lastUpdated":"2026-10-11T16:40:20.153Z","quality":{"calls30d":8,"uniquePayers30d":4,"lastCalledAt":"2026-10-11T16:40:19.786Z"},"metadata":{"serviceName":"Private LLM Inference - Long","extensions":{"bazaar":{"info":{"input":{"body":{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"hello","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":1,"prompt_tokens":30,"total_tokens":31},"x402":{"charged":"$0.01","inference_ms":1830,"output_cap":8192,"tier":"long","tokens_out":1}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"max_tokens":{"description":"Optional output token ceiling. This tier caps output at 8192 tokens - higher values are clamped to 8192, not rejected. Use the long/extended tiers for bigger outputs.","minimum":1,"type":"integer"},"messages":{"description":"OpenAI chat messages (system/user/assistant).","items":{"properties":{"content":{"type":"string"},"role":{"enum":["system","user","assistant"],"type":"string"}},"required":["role","content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.","type":"string"},"temperature":{"maximum":2,"minimum":0,"type":"number"}},"required":["messages"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}}},"liveness":{"reliability":null},"verified":false,"featured":false},{"id":35601,"slug":"35601","resource":"https://api.erb-llm.com/v1/embeddings","description":"Privacy-first OpenAI-compatible text embeddings (768 dims) from a local encoder on dedicated hardware - your text never reaches a third-party cloud. Send {\"input\": string or array of up to 64 texts}; receive standard OpenAI embeddings JSON with usage. Built for RAG, semantic search, dedupe and clustering in agent pipelines. ~2,000-token limit per text. Pay per call in USDC on Base (x402), no API key or account.","type":"http","serviceName":"Private LLM Embeddings","resourceType":"AI Inference","x402Version":2,"accepts":[{"scheme":"exact","network":"eip155:8453","payTo":"0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8","asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","amount":"1000","amountUsd":0.001,"maxTimeoutSeconds":300}],"outputSchema":{"properties":{"example":{"properties":{"data":{"items":{"properties":{"embedding":{"items":{"type":"number"},"type":"array"},"index":{"type":"integer"},"object":{"const":"embedding"}},"type":"object"},"type":"array"},"model":{"type":"string"},"object":{"const":"list"},"usage":{"properties":{"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"},"extensions":{"bazaar":{"info":{"input":{"body":{"input":["The quick brown fox jumps over the lazy dog","A fast brown fox leaps over a sleepy hound"]},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"data":[{"embedding":[0.0123,-0.0456,0.0789],"index":0,"object":"embedding"},{"embedding":[0.0124,-0.0452,0.0331],"index":1,"object":"embedding"}],"model":"text-embedding-nomic-embed-text-v1.5","object":"list","usage":{"prompt_tokens":24,"total_tokens":24},"x402":{"charged":"$0.001","inference_ms":420,"texts":2,"tier":"embed"}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"input":{"description":"One or more texts to embed (a single string also works). Keep each text under ~2,000 tokens; batches above 64 texts are clamped to the first 64 (never rejected after paying).","items":{"type":"string"},"type":"array"},"model":{"description":"Optional. Default: the gateway's local embedding model (nomic-embed-text-v1.5).","type":"string"}},"required":["input"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"data":{"items":{"properties":{"embedding":{"items":{"type":"number"},"type":"array"},"index":{"type":"integer"},"object":{"const":"embedding"}},"type":"object"},"type":"array"},"model":{"type":"string"},"object":{"const":"list"},"usage":{"properties":{"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}},"tags":["embeddings","vector","rag","semantic-search","usdc","bazaar"],"sourceHost":"api.erb-llm.com","lastUpdated":"2026-10-11T15:42:19.042Z","quality":{"calls30d":7,"uniquePayers30d":3,"lastCalledAt":"2026-10-11T15:42:18.678Z"},"metadata":{"serviceName":"Private LLM Embeddings","extensions":{"bazaar":{"info":{"input":{"body":{"input":["The quick brown fox jumps over the lazy dog","A fast brown fox leaps over a sleepy hound"]},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"data":[{"embedding":[0.0123,-0.0456,0.0789],"index":0,"object":"embedding"},{"embedding":[0.0124,-0.0452,0.0331],"index":1,"object":"embedding"}],"model":"text-embedding-nomic-embed-text-v1.5","object":"list","usage":{"prompt_tokens":24,"total_tokens":24},"x402":{"charged":"$0.001","inference_ms":420,"texts":2,"tier":"embed"}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"input":{"description":"One or more texts to embed (a single string also works). Keep each text under ~2,000 tokens; batches above 64 texts are clamped to the first 64 (never rejected after paying).","items":{"type":"string"},"type":"array"},"model":{"description":"Optional. Default: the gateway's local embedding model (nomic-embed-text-v1.5).","type":"string"}},"required":["input"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"data":{"items":{"properties":{"embedding":{"items":{"type":"number"},"type":"array"},"index":{"type":"integer"},"object":{"const":"embedding"}},"type":"object"},"type":"array"},"model":{"type":"string"},"object":{"const":"list"},"usage":{"properties":{"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}}},"liveness":{"reliability":null},"verified":false,"featured":false},{"id":35602,"slug":"35602","resource":"https://api.erb-llm.com/v1/extended","description":"Privacy-first extended inference: the highest output cap (32,768 tokens) on a local open-weight model on dedicated hardware - prompts never reach OpenAI/Anthropic or any third-party cloud. OpenAI-compatible chat completions for long-form writing, reports, full document drafts, large code outputs (messages array in, chat.completion JSON out). Pay per call in USDC on Base (x402), no API key or account. Pick the cheaper quick/long tiers for shorter work.","type":"http","serviceName":"Private LLM Inference - XL","resourceType":"AI Inference","x402Version":2,"accepts":[{"scheme":"exact","network":"eip155:8453","payTo":"0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8","asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","amount":"50000","amountUsd":0.05,"maxTimeoutSeconds":300}],"outputSchema":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"},"extensions":{"bazaar":{"info":{"input":{"body":{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"hello","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":1,"prompt_tokens":30,"total_tokens":31},"x402":{"charged":"$0.05","inference_ms":1830,"output_cap":32768,"tier":"extended","tokens_out":1}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"max_tokens":{"description":"Optional output token ceiling. This tier caps output at 32768 tokens - higher values are clamped to 32768, not rejected. Use the long/extended tiers for bigger outputs.","minimum":1,"type":"integer"},"messages":{"description":"OpenAI chat messages (system/user/assistant).","items":{"properties":{"content":{"type":"string"},"role":{"enum":["system","user","assistant"],"type":"string"}},"required":["role","content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.","type":"string"},"temperature":{"maximum":2,"minimum":0,"type":"number"}},"required":["messages"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}},"tags":["llm","longform","inference","private","openai-compatible","bazaar"],"sourceHost":"api.erb-llm.com","lastUpdated":"2026-10-11T15:42:06.721Z","quality":{"calls30d":6,"uniquePayers30d":1,"lastCalledAt":"2026-10-11T15:42:06.333Z"},"metadata":{"serviceName":"Private LLM Inference - XL","extensions":{"bazaar":{"info":{"input":{"body":{"messages":[{"content":"You are a helpful assistant.","role":"system"},{"content":"Reply with exactly one word: hello","role":"user"}],"model":"qwen/qwen3.8-27b","temperature":0.2},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"hello","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":1,"prompt_tokens":30,"total_tokens":31},"x402":{"charged":"$0.05","inference_ms":1830,"output_cap":32768,"tier":"extended","tokens_out":1}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"max_tokens":{"description":"Optional output token ceiling. This tier caps output at 32768 tokens - higher values are clamped to 32768, not rejected. Use the long/extended tiers for bigger outputs.","minimum":1,"type":"integer"},"messages":{"description":"OpenAI chat messages (system/user/assistant).","items":{"properties":{"content":{"type":"string"},"role":{"enum":["system","user","assistant"],"type":"string"}},"required":["role","content"],"type":"object"},"minItems":1,"type":"array"},"model":{"description":"Optional. The server runs one pinned model; any value is accepted but the pinned model serves the call.","type":"string"},"temperature":{"maximum":2,"minimum":0,"type":"number"}},"required":["messages"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}}},"liveness":{"reliability":null},"verified":false,"featured":false},{"id":35600,"slug":"35600","resource":"https://api.erb-llm.com/v1/vision","description":"Privacy-first OpenAI-compatible vision: a local vision-language model on dedicated hardware understands your images - they never reach OpenAI/Anthropic or any third-party cloud. Send a public image URL plus a prompt (or OpenAI image_url messages); receive a standard chat.completion JSON answering about the image. Up to 4 images per call (more are clamped). Pay per call in USDC on Base (x402), no API key.","type":"http","serviceName":"Private LLM Vision","resourceType":"AI Inference","x402Version":2,"accepts":[{"scheme":"exact","network":"eip155:8453","payTo":"0x23976FB6Af8f7fE8756730f0473fB7FfaC531ee8","asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","amount":"20000","amountUsd":0.02,"maxTimeoutSeconds":300}],"outputSchema":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"},"extensions":{"bazaar":{"info":{"input":{"body":{"image":"https://example.com/photo.jpg","model":"qwen/qwen3.8-27b","prompt":"What is in this image?"},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"A golden retriever running through a grassy field.","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":12,"prompt_tokens":60,"total_tokens":72},"x402":{"charged":"$0.02","inference_ms":2400,"tier":"vision","tokens_out":12}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"image":{"description":"A public https:// image URL (simple form). Use `image`+`prompt`, or the full OpenAI `messages` array with image_url parts.","type":"string"},"max_tokens":{"description":"Optional output cap. Default: the full 2,048-token vision cap.","type":"integer"},"messages":{"description":"OpenAI chat messages using image_url content parts (full form). Up to 4 images per call; more are clamped to the first 4.","items":{"type":"object"},"type":"array"},"model":{"description":"Optional. Default: the gateway's local vision-language model.","type":"string"},"prompt":{"description":"What to do with the image (used with `image`). Default: 'Describe this image.'","type":"string"}},"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}},"tags":["vision","image-understanding","multimodal","private","usdc","bazaar"],"sourceHost":"api.erb-llm.com","lastUpdated":"2026-10-11T15:42:28.805Z","quality":{"calls30d":4,"uniquePayers30d":1,"lastCalledAt":"2026-10-11T15:42:28.566Z"},"metadata":{"serviceName":"Private LLM Vision","extensions":{"bazaar":{"info":{"input":{"body":{"image":"https://example.com/photo.jpg","model":"qwen/qwen3.8-27b","prompt":"What is in this image?"},"bodyType":"json","method":"POST","type":"http"},"output":{"example":{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"A golden retriever running through a grassy field.","role":"assistant"}}],"id":"chatcmpl-abc123","model":"qwen/qwen3.8-27b","object":"chat.completion","usage":{"completion_tokens":12,"prompt_tokens":60,"total_tokens":72},"x402":{"charged":"$0.02","inference_ms":2400,"tier":"vision","tokens_out":12}},"type":"json"}},"schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"image":{"description":"A public https:// image URL (simple form). Use `image`+`prompt`, or the full OpenAI `messages` array with image_url parts.","type":"string"},"max_tokens":{"description":"Optional output cap. Default: the full 2,048-token vision cap.","type":"integer"},"messages":{"description":"OpenAI chat messages using image_url content parts (full form). Up to 4 images per call; more are clamped to the first 4.","items":{"type":"object"},"type":"array"},"model":{"description":"Optional. Default: the gateway's local vision-language model.","type":"string"},"prompt":{"description":"What to do with the image (used with `image`). Default: 'Describe this image.'","type":"string"}},"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"choices":{"items":{"properties":{"finish_reason":{"type":"string"},"index":{"type":"integer"},"message":{"properties":{"content":{"type":"string"},"role":{"type":"string"}},"type":"object"}},"type":"object"},"type":"array"},"id":{"type":"string"},"model":{"type":"string"},"object":{"const":"chat.completion"},"usage":{"properties":{"completion_tokens":{"type":"integer"},"prompt_tokens":{"type":"integer"},"total_tokens":{"type":"integer"}},"type":"object"},"x402":{"description":"Billing stamp added by the gateway.","properties":{"capped_from":{"type":"integer"},"charged":{"type":"string"},"inference_ms":{"type":"integer"},"note":{"type":"string"},"output_cap":{"type":"integer"},"tier":{"type":"string"},"tokens_out":{"type":"integer"}},"type":"object"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"}}}},"liveness":{"reliability":null},"verified":false,"featured":false}]}