{"info":{"title":"Vexa AI API","description":"Multi-provider AI service offering text generation, image generation, and model management","version":"1.0.0","base_url":"https://vexa-ai.pages.dev","timestamp":"2026-06-14T02:59:27.305Z","status":"operational"},"defaults":{"chat_model":"DeepAI","image_model":"hd","query_model":"DeepAI","image_preference":"speed"},"statistics":{"available_text_models":30,"available_image_models":6,"enabled_providers":6},"endpoints":{"/":{"description":"API documentation and information","methods":["GET"],"parameters":{"format":{"type":"string","enum":["json","html"],"default":"json","description":"Response format"},"examples":{"type":"boolean","default":"true","description":"Include usage examples"}}},"/chat":{"description":"Chat completion with conversation history","methods":["POST","OPTIONS"],"parameters":{"model":{"type":"string","default":"DeepAI","description":"AI model to use"},"messages":{"type":"array","required":true,"description":"Array of message objects"},"stream":{"type":"boolean","default":"false","description":"Enable streaming response"}},"message_format":{"role":{"type":"string","enum":["system","user","assistant"],"required":true},"content":{"type":"string","required":true,"description":"Message content"}},"examples":{"basic_chat":{"description":"Simple chat request","request":"POST /chat {\"model\":\"DeepAI\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello, how are you?\"}]}","curl":"curl -X POST https://vexa-ai.pages.dev/chat -H \"Content-Type: application/json\" -d '{\"model\":\"DeepAI\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'"},"streaming":{"description":"Streaming chat response","request":"POST /chat {\"model\":\"DeepAI\",\"messages\":[{\"role\":\"user\",\"content\":\"Tell me a story\"}],\"stream\":true}","note":"Returns server-sent events (SSE) for real-time streaming"}}},"/image":{"description":"Generate images from text prompts","methods":["GET","POST","OPTIONS"],"parameters":{"prompt":{"type":"string","required":true,"description":"Text description of the image to generate"},"model":{"type":"string","default":"hd","enum":["hd","flux","turbo-img","kontext","seedream","nanobanana"],"description":"Image generation model"},"preference":{"type":"string","enum":["speed","quality"],"default":"speed","description":"Generation preference"}},"available_models":[{"name":"hd","label":"HD","description":"Standard HD generation - DeepAI"},{"name":"flux","label":"Flux","description":"Fast, high quality - default"},{"name":"turbo-img","label":"Flux Turbo","description":"Fastest generation"},{"name":"kontext","label":"Flux Kontext","description":"Instruction-following edits"},{"name":"seedream","label":"Seedream 3","description":"ByteDance - photorealistic"},{"name":"nanobanana","label":"Nano Banana","description":"Gemini-powered - high detail"}],"examples":{"get_request":{"description":"Generate image via GET","request":"GET /image?q=a+cat","curl":"curl \"https://vexa-ai.pages.dev/image?q=a+cat\""},"post_request":{"description":"Generate image via POST","request":"POST /image {\"prompt\":\"a cat\",\"model\":\"hd\",\"preference\":\"speed\"}","curl":"curl -X POST https://vexa-ai.pages.dev/image -H \"Content-Type: application/json\" -d '{\"prompt\":\"a cat\",\"model\":\"hd\"}'"}}},"/image/proxy/:id":{"description":"Proxy for serving generated images","methods":["GET"],"parameters":{"id":{"type":"string","required":true,"description":"Image identifier from generation response"}},"examples":{"proxy_image":{"description":"Access generated image","request":"GET /image/proxy/abc123","curl":"curl \"https://vexa-ai.pages.dev/image/proxy/abc123\" --output image.png"}}},"/query":{"description":"Simple single-prompt text generation","methods":["GET","POST","OPTIONS"],"parameters":{"prompt":{"type":"string","required":true,"description":"Text prompt for generation"},"model":{"type":"string","default":"DeepAI","description":"AI model to use"}},"examples":{"get_request":{"description":"Query via GET parameters","request":"GET /query?q=What+is+AI?","curl":"curl \"https://vexa-ai.pages.dev/query?q=What+is+AI?\""},"post_request":{"description":"Query via POST body","request":"POST /query {\"prompt\":\"What is AI?\",\"model\":\"DeepAI\"}","curl":"curl -X POST https://vexa-ai.pages.dev/query -H \"Content-Type: application/json\" -d '{\"prompt\":\"What is AI?\",\"model\":\"DeepAI\"}'"}}},"/models":{"description":"List available AI models and their status","methods":["GET","OPTIONS"],"parameters":{"details":{"type":"boolean","default":"false","description":"Include detailed model information"},"type":{"type":"string","enum":["text","image"],"description":"Filter by model type"}},"examples":{"list_models":{"description":"Get all available models","request":"GET /models","curl":"curl \"https://vexa-ai.pages.dev/models\""},"detailed_info":{"description":"Get detailed model information","request":"GET /models?details=true","curl":"curl \"https://vexa-ai.pages.dev/models?details=true\""}}},"/health":{"description":"System health check and service status","methods":["GET","OPTIONS"],"parameters":{"skip_models":{"type":"boolean","default":"false","description":"Skip individual model health checks"}},"examples":{"health_check":{"description":"Full system health check","request":"GET /health","curl":"curl \"https://vexa-ai.pages.dev/health\""},"quick_check":{"description":"Quick health check without model testing","request":"GET /health?skip_models=true","curl":"curl \"https://vexa-ai.pages.dev/health?skip_models=true\""}}}},"response_formats":{"success":{"description":"Successful API response","structure":{"success":true,"data":"response_data","model":"model_used","elapsed_ms":"response_time_ms"}},"error":{"description":"Error response","structure":{"success":false,"error":"error_message","detail":"detailed_error_info"}},"streaming":{"description":"Server-sent events format for streaming","format":"data: {JSON_OBJECT}\\n\\n","note":"Ends with 'data: [DONE]\\n\\n'"}},"usage_notes":{"authentication":"No API key required - rate limits apply","rate_limits":"Requests are limited per IP address","model_availability":"Models may become unavailable based on provider status","image_generation":"Images are cached and served via proxy endpoint","streaming":"Use stream=true for real-time responses in chat endpoint"},"providers":{"enabled":["toolbaz","deepai","pollinations","dolphin","talkai","aifree"],"disabled":[]}}