18 publishers available
by SerenEmbed
Text embedding pipeline service that fetches data from x402 publishers, chunks text, generates embeddings via OpenAI, and writes vectors to PostgreSQL/pgvector destinations.
by OpenAI Embeddings
Create text embeddings using OpenAI text-embedding-3-small and text-embedding-3-large models for semantic search, clustering, and recommendations.
by SerenModels
Multi-model LLM inference with automatic routing, failover, and unified billing. Access over 300 models from over 60 model providers including OpenAI, Anthropic, Google, Meta, Mistral, and more through a single OpenAI-compatible API.
by Firecrawl
AI-powered web scraping API that turns websites into LLM-ready markdown or structured data. Supports scraping single pages, crawling entire sites, mapping website structures, and searching the web with one API call.
by Perplexity
Perplexity is an AI-powered search engine that provides accurate, up-to-date answers with citations. Access raw web search results or grounded LLM responses through Sonar models.
by Moonshot AI
Moonshot AI Kimi K2 - trillion-parameter MoE model with 256K context. State-of-the-art performance in coding, math, and reasoning. OpenAI-compatible API.
by OpenAI
Access OpenAI GPT-5.2, the best model for coding and agentic tasks across industries. Also supports GPT-5 mini for fast, affordable responses on well-defined tasks.
by SerenCouncil
Multi-model AI consensus service. Your query is deliberated by 5 diverse AI models (Claude, GPT-5, Kimi, Gemini, Sonar), each critiques the others, then a Chairman synthesizes the final answer. Better answers through structured disagreement - reduces hallucinations and catches errors individual models miss.
by SerenWhisper
Speech-to-Text transcription service for voice input. Supports mp3, mp4, wav, webm audio formats up to 25MB with 97+ language support.
by Nano Banana
AI image generation powered by Google Gemini 3 Pro Image (Nano Banana Pro). Generate high-resolution images up to 4K, edit existing images, blend multiple references, and render text with exceptional accuracy. Supports multiple aspect ratios and multi-turn conversational refinement.
by Google Gemini 3 Pro
Google Gemini 3 Pro (google/gemini-3-pro-preview) via OpenRouter - flagship frontier model for high-precision multimodal reasoning with 1M token context. Supports text, image, video, audio, code, and step-by-step reasoning.
by xAI Grok Code Fast
xAI Grok Code Fast (x-ai/grok-code-fast-1) via OpenRouter - optimized for code generation with fast response times. Input: $0.20/M tokens, Output: $1.50/M tokens.
by Kling AI
AI-powered video and image generation API. Create stunning videos from text or images with Kling-Video-O1, V2.5-Turbo, and V2.1 models. Generate images with kling-image-o1. Supports text-to-video (5-10 sec), image-to-video, lip-sync, and virtual try-on.
by SerenSwarm
Bounty network for AI agents to collaborate, stake tokens, submit contributions, vote on solutions, and earn rewards
by ExoPriors Alignment Scry
SQL-queryable corpus of 60M+ alignment research documents including LessWrong posts, EA Forum, ArXiv papers, tweets, and HackerNews comments. Supports BM25 lexical search via alignment.search(), semantic search with stored embeddings, and full SQL aggregations. Public read-only access with adaptive 20-120s query timeouts.
by Eleven Labs
AI voice synthesis API for text-to-speech, voice cloning, and audio generation. Access 5,000+ voices in 70+ languages with ultra-low 75ms latency. Create natural-sounding speech with industry-leading quality.
by Anthropic Claude API
Access Claude AI models including Claude Sonnet 4.5, Claude Opus 4.5, and Claude Haiku. Chat completions, message batches, token counting, and more.
by OpenAI Images
AI Agents get access to OpenAI DALL-E 3, GPT-Image-1, and DALL-E 2 models for image generation, editing, and variations.
