{ "openapi": "3.1.0", "info": { "title": "NoJunk LLM", "version": "1.0.0", "description": "Pay-per-call, OpenAI-compatible LLM API for agents: POST /v1/chat/completions (Llama 3.3 70B or Qwen 2.5 Coder 32B, up to 32,000 characters of messages, up to 1,024 output tokens, optional JSON mode) and POST /v1/embeddings (BGE-M3, 1,024 dimensions, up to 32 inputs per call). Point any OpenAI client at this base URL and pay per request in USDC on Base via x402: no API key, no account, no rate limits. You are only charged when a valid result is returned.", "x-guidance": "OpenAI-compatible LLM API paid per call in USDC on Base via x402 (you are only charged when a valid result is returned; all 4xx/5xx are free). Use it like OpenAI: set base_url to https://nojunk-llm.mick8511.workers.dev/v1 (any api_key value), send the normal JSON bodies, and attach the x402 PAYMENT-SIGNATURE header with an x402 client (for example x402-fetch, or the @x402/fetch wrapper around your HTTP client): the first call without payment returns 402 with the exact requirements. POST /v1/chat/completions {model?: llama-3.3-70b|qwen2.5-coder-32b, messages: [{role: system|user|assistant, content}], max_tokens?: 1-1024, temperature?: 0-2, top_p?, response_format?: {type: \"json_object\"}} -> standard chat.completion object, costs $0.005 per call regardless of length (up to 32000 characters in, 1024 tokens out); \"gpt-4o-mini\" is accepted as an alias of llama-3.3-70b; streaming, tools and image content are not supported (400). POST /v1/embeddings {input: string | string[] (1-32, each <= 8000 chars), model?: bge-m3} -> standard embeddings list (1024 dimensions), costs $0.001 per call. GET /v1/models is free. Best for: agents that need an LLM or embeddings without an API key or account, batch summarization/classification/extraction, RAG indexing and semantic search." }, "servers": [ { "url": "https://nojunk-llm.mick8511.workers.dev" } ], "paths": { "/v1/chat/completions": { "post": { "operationId": "createChatCompletion", "summary": "OpenAI-compatible chat completion (Llama 3.3 70B or Qwen 2.5 Coder 32B)", "tags": [ "AI", "LLM", "Chat", "OpenAI-compatible" ], "x-payment-info": { "price": { "mode": "fixed", "currency": "USD", "amount": "0.005000" }, "protocols": [ { "x402": {} } ] }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "model": { "type": "string", "enum": [ "llama-3.3-70b", "qwen2.5-coder-32b", "gpt-4o-mini" ], "default": "llama-3.3-70b", "description": "llama-3.3-70b (Llama 3.3 70B, general purpose) or qwen2.5-coder-32b (code). \"gpt-4o-mini\" is accepted as an alias of the default so stock OpenAI client code works unchanged." }, "messages": { "type": "array", "minItems": 1, "maxItems": 200, "items": { "type": "object", "properties": { "role": { "type": "string", "enum": [ "system", "user", "assistant" ] }, "content": { "type": "string" } }, "required": [ "role", "content" ] }, "description": "The conversation; total content across all messages is capped at 32000 characters (400 above that). Content must be plain strings." }, "max_tokens": { "type": "integer", "minimum": 1, "maximum": 1024, "default": 512, "description": "Maximum completion tokens" }, "temperature": { "type": "number", "minimum": 0, "maximum": 2, "default": 0.7 }, "top_p": { "type": "number", "exclusiveMinimum": 0, "maximum": 1, "description": "Nucleus sampling" }, "response_format": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "json_object", "text" ] } }, "required": [ "type" ], "description": "{\"type\": \"json_object\"} forces a JSON object reply (also say \"JSON\" in your prompt)" }, "stream": { "type": "boolean", "const": false, "description": "Streaming is not supported; stream: true returns 400" } }, "required": [ "messages" ] } } } }, "responses": { "200": { "description": "Result", "content": { "application/json": { "schema": { "type": "object", "properties": { "id": { "type": "string", "description": "chatcmpl-" }, "object": { "type": "string", "const": "chat.completion" }, "created": { "type": "integer", "description": "Unix seconds" }, "model": { "type": "string", "enum": [ "llama-3.3-70b", "qwen2.5-coder-32b" ] }, "choices": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "integer" }, "message": { "type": "object", "properties": { "role": { "type": "string", "const": "assistant" }, "content": { "type": "string" } }, "required": [ "role", "content" ] }, "finish_reason": { "type": "string", "enum": [ "stop", "length" ] } }, "required": [ "index", "message", "finish_reason" ] } }, "usage": { "type": "object", "properties": { "prompt_tokens": { "type": "integer" }, "completion_tokens": { "type": "integer" }, "total_tokens": { "type": "integer" } }, "required": [ "prompt_tokens", "completion_tokens", "total_tokens" ] } }, "required": [ "id", "object", "created", "model", "choices", "usage" ] } } } }, "400": { "description": "Invalid input (no charge)" }, "402": { "description": "Payment Required" }, "413": { "description": "Request body larger than 160 KB (no charge)" }, "502": { "description": "AI model temporarily unavailable or returned an unusable result (no charge)" } } } }, "/v1/embeddings": { "post": { "operationId": "createEmbedding", "summary": "OpenAI-compatible text embeddings (BGE-M3, 1024 dimensions)", "tags": [ "AI", "Embeddings", "OpenAI-compatible" ], "x-payment-info": { "price": { "mode": "fixed", "currency": "USD", "amount": "0.001000" }, "protocols": [ { "x402": {} } ] }, "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "properties": { "input": { "oneOf": [ { "type": "string", "minLength": 1, "maxLength": 8000 }, { "type": "array", "minItems": 1, "maxItems": 32, "items": { "type": "string", "minLength": 1, "maxLength": 8000 } } ], "description": "Text(s) to embed: one string or up to 32 strings, each at most 8000 characters" }, "model": { "type": "string", "enum": [ "bge-m3" ], "default": "bge-m3" }, "encoding_format": { "type": "string", "enum": [ "float" ], "default": "float" } }, "required": [ "input" ] } } } }, "responses": { "200": { "description": "Result", "content": { "application/json": { "schema": { "type": "object", "properties": { "object": { "type": "string", "const": "list" }, "data": { "type": "array", "items": { "type": "object", "properties": { "object": { "type": "string", "const": "embedding" }, "index": { "type": "integer" }, "embedding": { "type": "array", "items": { "type": "number" }, "minItems": 1024, "maxItems": 1024 } }, "required": [ "object", "index", "embedding" ] }, "description": "One embedding per input, in input order" }, "model": { "type": "string", "const": "bge-m3" }, "usage": { "type": "object", "properties": { "prompt_tokens": { "type": "integer", "description": "Approximate (characters / 4)" }, "total_tokens": { "type": "integer" } }, "required": [ "prompt_tokens", "total_tokens" ] } }, "required": [ "object", "data", "model", "usage" ] } } } }, "400": { "description": "Invalid input (no charge)" }, "402": { "description": "Payment Required" }, "413": { "description": "Request body larger than 160 KB (no charge)" }, "502": { "description": "AI model temporarily unavailable or returned an unusable result (no charge)" } } } }, "/v1/models": { "get": { "operationId": "listModels", "summary": "List available models and their per-call prices (free)", "tags": [ "OpenAI-compatible" ], "responses": { "200": { "description": "Model list", "content": { "application/json": { "schema": { "type": "object", "properties": { "object": { "type": "string", "const": "list" }, "data": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string" }, "object": { "type": "string", "const": "model" }, "owned_by": { "type": "string" }, "pricing_usd_per_call": { "type": "number" } }, "required": [ "id", "object", "owned_by", "pricing_usd_per_call" ] } } }, "required": [ "object", "data" ] } } } } } } } } }