{"id":46211,"name":"Pictomancer.ai","description":"Agent-to-agent image processing service. Resize, convert, compress, and pipeline images via REST, MCP, or A2A.","card_url":"https://api.pictomancer.ai/.well-known/agent.json","endpoint":"https://api.pictomancer.ai/a2a","protocol_version":"1.0","first_seen":"2026-10-12T05:08:32.928692+00:00","last_verified":"2026-10-12T07:16:41.979888+00:00","card":{"url":"https://api.pictomancer.ai/a2a","name":"Pictomancer.ai","skills":[{"id":"analyze_image","name":"Analyze image","tags":["image","metadata","analyze","size","provenance","c2pa"],"examples":["How big is this image? https://example.com/photo.jpg","Get the file size of this PNG"],"inputModes":["application/json"],"description":"Fetch an image and return metadata: file size, dimensions, source format, per-model vision token cost, and whether it carries a C2PA (Content Credentials) manifest. Accepts a public URL or base64-encoded image.","outputModes":["application/json"]},{"id":"resize_image","name":"Resize image","tags":["image","resize","scale","dimensions","smart-crop","fill"],"examples":["Resize this image to half size: https://example.com/photo.jpg","Scale this image by 0.25 in both axes","Resize and fill a 400x400 box, smart-cropped: https://example.com/photo.jpg"],"inputModes":["application/json"],"description":"Scale an image by a factor, or fill an exact box. Supports uniform scaling (scale) or independent axes (scale_x, scale_y). Or set width+height for fill mode: resize and smart-crop to those exact dimensions in one call (optional gravity: attention, entropy, centre). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen. Output formats: jpeg, png, webp, tiff, gif, avif.","outputModes":["image/jpeg","image/png","image/webp"]},{"id":"compress_image","name":"Compress image","tags":["image","compress","optimize","quality","file-size","ssim","sharpen","denoise","equalize","enhance"],"examples":["Compress this JPEG to q=60: https://example.com/photo.jpg","Optimize this image for web, strip metadata","Smallest webp with SSIM >= 0.95: https://example.com/photo.jpg","Denoise and sharpen this scan, then compress it"],"inputModes":["application/json"],"description":"Re-encode an image with q (1-100) and format options to reduce file size. Supports q (quality), strip, compression. Formats: jpeg, png, webp, tiff, gif, avif. Or set quality_target (0-1] instead of q: the worker searches for the smallest file with SSIM at or above the target (jpeg, webp, avif) and reports the achieved SSIM, final q and encode count. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.","outputModes":["image/jpeg","image/png","image/webp"]},{"id":"convert_image","name":"Convert image format","tags":["image","convert","format","webp","avif","png","jpeg"],"examples":["Convert this PNG to WebP: https://example.com/image.png","Convert to AVIF with q=50: https://example.com/photo.jpg","Convert to JPEG with q=85, strip EXIF"],"inputModes":["application/json"],"description":"Convert an image to a different format. Supports: jpeg, png, webp, tiff, gif, avif. Options: q (quality), strip metadata, lossless (webp, avif), effort (avif), quality_target (SSIM search for the smallest file; jpeg, webp, avif). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.","outputModes":["image/jpeg","image/png","image/webp","image/tiff","image/gif","image/avif"]},{"id":"crop_image","name":"Crop image","tags":["image","crop","cut","region","trim","smart-crop","gravity"],"examples":["Crop a 200x200 square at (10, 10): https://example.com/photo.jpg","Smart-crop this to 512x512, focused on the subject: https://example.com/photo.jpg","Trim the white border off this scanned page: https://example.com/photo.jpg"],"inputModes":["application/json"],"description":"Extract a rectangular region from an image, in one of three modes. Manual: top-left corner (x, y) and dimensions (width, height) in pixels. Smart crop: gravity (attention, entropy, centre) plus width and height; the window is picked automatically. Trim: trim=true (optional threshold) removes a uniform background border via content detection. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen. Output formats: jpeg, png, webp, tiff, gif, avif.","outputModes":["image/jpeg","image/png","image/webp"]},{"id":"optimize_for_vision","name":"Optimize image for a vision model","tags":["image","vision","tokens","llm","resize","cost"],"examples":["Prepare this screenshot for claude-opus-5: https://example.com/shot.png","Resize this photo for gpt-4o","Get this under 1500 tokens for claude-opus-5"],"inputModes":["application/json"],"description":"Resize an image to the largest size a given vision model still benefits from, and report what it costs that model in tokens before and after. Every provider downscales oversized input before counting, so this saves bytes and upload latency rather than tokens; pass max_tokens to trade resolution for tokens. Supported models: claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-sonnet-5, claude-opus-4-6, claude-sonnet-4-6, claude-opus-4-5, claude-sonnet-4-5, claude-haiku-4-5, gpt-4o, gpt-4.1, gpt-4o-mini, o1, o3, gemini-2.5-pro, gemini-2.5-flash.","outputModes":["image/jpeg","image/png","image/webp"]},{"id":"optimize_generated_image","name":"Optimize an AI-generated image for the web","tags":["image","generated","ai-generated","gpt-image","dall-e","flux","midjourney","stable-diffusion","webp","avif","optimize","web"],"examples":["Optimize this gpt-image output for my website: https://example.com/gen.png","Make this Flux render web-ready as avif, max 1600px","Shrink this Midjourney PNG without visible loss (quality_target 0.95)"],"inputModes":["application/json"],"description":"The step after image generation: turn the 2-8 MB PNG that gpt-image, DALL-E, Flux, Midjourney or Stable Diffusion returned into a web-ready webp (default), avif, jpeg or png. Metadata stripped, transparency kept, optional max_dimension cap (never upscales), optional q or quality_target (SSIM). Same price as convert; if the result is not smaller it is free. Reports bytes before and after. The input's C2PA manifest is reported but not carried over: re-encoding invalidates it.","outputModes":["image/webp","image/avif","image/jpeg","image/png"]},{"id":"image_pipeline","name":"Image processing pipeline","tags":["image","pipeline","batch","chain","multi-step"],"examples":["Resize to 50% then convert to WebP: https://example.com/photo.jpg","Crop, resize, and compress this image in one call"],"inputModes":["application/json"],"description":"Chain multiple image operations in sequence (max 10). Operations: resize, compress, convert, crop. Each step receives the output of the previous one.","outputModes":["image/jpeg","image/png","image/webp"]}],"pricing":{"model":"pay-per-request","network":"base","currency":"USDC","free_tier":"50 requests per agent","base_prices":{"crop":"$0.001","resize":"$0.001","analyze":"$0.0","convert":"$0.002","compress":"$0.001","optimize_generated":"$0.002","optimize_for_vision":"$0.001"},"max_cost_header":"X-Max-Cost-USD","payment_protocol":"x402","size_multipliers":{"1MB_5MB":"1.5x","5MB_10MB":"2.0x","10MB_50MB":"3.0x","under_1MB":"1.0x"},"estimate_endpoint":"/v1/estimate","format_surcharges":{"avif":"$0.001"},"feature_surcharges":{"quality_target":"$0.004"}},"version":"0.1.0","provider":{"url":"https://pictomancer.ai","organization":"Pictomancer.ai"},"security":[],"interfaces":[{"url":"https://api.pictomancer.ai/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"},{"url":"https://api.pictomancer.ai","protocolBinding":"HTTP+JSON","protocolVersion":"1.0"},{"url":"https://api.pictomancer.ai/mcp","protocolBinding":"MCP","protocolVersion":"1.0"}],"provenance":{"c2pa_detection":true,"output_carries_manifest":false},"description":"Agent-to-agent image processing service. Resize, convert, compress, and pipeline images via REST, MCP, or A2A.","capabilities":{"streaming":false,"extensions":[{"uri":"https://x402.org","params":{"chain":"base","token":"USDC","freeTier":50},"required":false,"description":"Pay-per-request in USDC on Base L2. First 50 requests free per agent."}],"extendedAgentCard":true,"pushNotifications":false},"protocolVersion":"1.0","securitySchemes":{},"defaultInputModes":["application/json"],"defaultOutputModes":["application/json","image/jpeg","image/png","image/webp"],"preferredTransport":"JSONRPC","supportedInterfaces":[{"url":"https://api.pictomancer.ai/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"},{"url":"https://api.pictomancer.ai","protocolBinding":"HTTP+JSON","protocolVersion":"1.0"},{"url":"https://api.pictomancer.ai/mcp","protocolBinding":"MCP","protocolVersion":"1.0"}]},"signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-12T07:16:41.979888+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Global A2A Registry","source_url":"https://api.a2a-registry.org/public/agents","last_check":{"checked_at":"2026-10-12T07:16:41.979888+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://api.pictomancer.ai/.well-known/agent.json"],"also_observed_in":[{"source_name":"A2A Registry","source_url":"https://a2aregistry.org/api/agents","last_seen":"2026-10-12T05:15:24.465812+00:00"},{"source_name":"Global A2A Registry","source_url":"https://api.a2a-registry.org/public/agents","last_seen":"2026-10-12T05:42:48.241252+00:00"}],"skills":[{"skill_id":"analyze_image","name":"Analyze image","description":"Fetch an image and return metadata: file size, dimensions, source format, per-model vision token cost, and whether it carries a C2PA (Content Credentials) manifest. Accepts a public URL or base64-encoded image.","tags":["image","metadata","analyze","size","provenance","c2pa"],"quality_warning":false},{"skill_id":"compress_image","name":"Compress image","description":"Re-encode an image with q (1-100) and format options to reduce file size. Supports q (quality), strip, compression. Formats: jpeg, png, webp, tiff, gif, avif. Or set quality_target (0-1] instead of q: the worker searches for the smallest file with SSIM at or above the target (jpeg, webp, avif) and reports the achieved SSIM, final q and encode count. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.","tags":["image","compress","optimize","quality","file-size","ssim","sharpen","denoise","equalize","enhance"],"quality_warning":false},{"skill_id":"convert_image","name":"Convert image format","description":"Convert an image to a different format. Supports: jpeg, png, webp, tiff, gif, avif. Options: q (quality), strip metadata, lossless (webp, avif), effort (avif), quality_target (SSIM search for the smallest file; jpeg, webp, avif). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen.","tags":["image","convert","format","webp","avif","png","jpeg"],"quality_warning":false},{"skill_id":"crop_image","name":"Crop image","description":"Extract a rectangular region from an image, in one of three modes. Manual: top-left corner (x, y) and dimensions (width, height) in pixels. Smart crop: gravity (attention, entropy, centre) plus width and height; the window is picked automatically. Trim: trim=true (optional threshold) removes a uniform background border via content detection. Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen. Output formats: jpeg, png, webp, tiff, gif, avif.","tags":["image","crop","cut","region","trim","smart-crop","gravity"],"quality_warning":false},{"skill_id":"image_pipeline","name":"Image processing pipeline","description":"Chain multiple image operations in sequence (max 10). Operations: resize, compress, convert, crop. Each step receives the output of the previous one.","tags":["image","pipeline","batch","chain","multi-step"],"quality_warning":false},{"skill_id":"optimize_generated_image","name":"Optimize an AI-generated image for the web","description":"The step after image generation: turn the 2-8 MB PNG that gpt-image, DALL-E, Flux, Midjourney or Stable Diffusion returned into a web-ready webp (default), avif, jpeg or png. Metadata stripped, transparency kept, optional max_dimension cap (never upscales), optional q or quality_target (SSIM). Same price as convert; if the result is not smaller it is free. Reports bytes before and after. The input's C2PA manifest is reported but not carried over: re-encoding invalidates it.","tags":["image","generated","ai-generated","gpt-image","dall-e","flux","midjourney","stable-diffusion","webp","avif","optimize","web"],"quality_warning":false},{"skill_id":"optimize_for_vision","name":"Optimize image for a vision model","description":"Resize an image to the largest size a given vision model still benefits from, and report what it costs that model in tokens before and after. Every provider downscales oversized input before counting, so this saves bytes and upload latency rather than tokens; pass max_tokens to trade resolution for tokens. Supported models: claude-opus-5, claude-opus-4-8, claude-opus-4-7, claude-sonnet-5, claude-opus-4-6, claude-sonnet-4-6, claude-opus-4-5, claude-sonnet-4-5, claude-haiku-4-5, gpt-4o, gpt-4.1, gpt-4o-mini, o1, o3, gemini-2.5-pro, gemini-2.5-flash.","tags":["image","vision","tokens","llm","resize","cost"],"quality_warning":false},{"skill_id":"resize_image","name":"Resize image","description":"Scale an image by a factor, or fill an exact box. Supports uniform scaling (scale) or independent axes (scale_x, scale_y). Or set width+height for fill mode: resize and smart-crop to those exact dimensions in one call (optional gravity: attention, entropy, centre). Optional enhancement modifiers: denoise (median, radius 1-3), equalize (auto-contrast), sharpen. Output formats: jpeg, png, webp, tiff, gif, avif.","tags":["image","resize","scale","dimensions","smart-crop","fill"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":2,"passed":2},"recent_checks":[{"card_url":"https://api.pictomancer.ai/.well-known/agent.json","checked_at":"2026-10-12T07:16:41.979888+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},{"card_url":"https://api.pictomancer.ai/.well-known/agent.json","checked_at":"2026-10-12T05:08:32.928692+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":{"checked_at":"2026-10-12T07:16:41.979888+00:00","success":true,"detail":"Valid TLS connection to advertised endpoint host; no A2A request sent"},"protocol_check":{"checked_at":"2026-10-12T05:08:32.928692+00:00","state":"a2a_response","http_status":200,"detail":"A2A error response to a read-only task lookup"},"x402_price_check":null,"events":[],"relationships":[],"verification":{"agent_card_url":"https://api.pictomancer.ai/.well-known/agent.json","last_successful_card_check":"2026-10-12T07:16:41.979888+00:00","latest_card_check":{"checked_at":"2026-10-12T07:16:41.979888+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-12T07:16:41.979888+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":"2026-10-12T07:16:41.979888+00:00","endpoint_tls_reachable":true,"protocol_check_state":"a2a_response","protocol_checked_at":"2026-10-12T05:08:32.928692+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null}}