← All headings
AI models & inference
995 listings from 505 providers, 778 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 351–375, one row per provider, those answering first · names and descriptions as their source publishes them
- Wattwatt.area21.ioUse when you need image embeddings or text embeddings in one 2048-dimension space for retrieval, RAG, semantic search, clustering, or dedup (Qwen3-VL-Embedding-2B, OpenAI-compatible). Batch up to 256 items per call, served 32 at a time. An x402 call is $0.002 when the request includes images, $0.001 for text-only. USDC on Base. 400 is a bad body, 413 is over 48 MiB, 429 means busy (Retry-After).Unreachablechecked Evidence 0/4x402x402 Bazaar2 payers1 more from area21.io
- LLM Router - Open-Weight Modelsapi.ai-open-models.comAn LLM router for an open-weight inference service. It analyzes your request, selects a suitable compatible model, runs the selected model, and returns its answer in OpenAI-compatible format.Unreachablechecked Evidence 0/4x402x402 Bazaar2 payers2 more from ai-open-models.com
- Algono Inferenceinference.algono.coLow-cost OpenAI-compatible Responses API inference over Solana USDC x402.Unreachablechecked Evidence 0/4x402x402 Bazaar2 payers
- app.heinrichstech.com/v1/cdp/pii-redactapp.heinrichstech.comBitBooth PII Redact: pay 0.008 USDC, strip emails, phones, SSNs, credit cards, IPv4 addresses, and hex-looking secrets from a text blob before passing it to an LLM. Compliance primitive for agents in regulated industries (health, finance, legal). Pure regex — no LLM inference, deterministic output.Unreachablechecked Evidence 0/4x402x402 Bazaar2 payers
- sovereign-x402-zeta.vercel.app/api/v1/chat/completionssovereign-x402-zeta.vercel.appAI chat completions API - pay per request with USDC on BaseUnreachablechecked Evidence 0/4x402x402 Bazaar1 payer
- uxus.finance/api/llmuxus.financeLLM chat completion. $0.01 USDC per call on Base, no API key. POST JSON { prompt } or { messages: [{ role, content }] }; optional model (OpenRouter slug) and max_tokens (default 800, max 2000). Falls back across up to 5 models so one outage does not fail the call. Returns { content, model, usage, latency_ms }.Unreachablechecked Evidence 0/4x402x402 Bazaar1 payer1 more from uxus.finance
- AIOptiTech Prompt Library promptapi.aioptitech.comAIOptiTech Prompt Library prompt body. Pay 0.05 USDC once for the prompt identified by the id path parameter. Personal use. An active subscription pass can read it without a second payment.Unreachablechecked Evidence 0/4x402x402 Bazaar1 payer
- agent.maximusmediahouse.com/v1/chat/completionsagent.maximusmediahouse.comUnreachablechecked Evidence 0/4x402x402 Bazaar1 payer
- Omni Terminalomniterminal.appBounded public Hyperliquid spot data with exact pair/token identity, source timestamps and explicit observation-only context. No perpetual ticker inference.Unreachablechecked Evidence 0/4x402x402 Bazaar1 payer1 more from omniterminal.app
- Koinelix LLM Responsesapi.koinelix.comLLM inference billed by token usage with a per-request minimum. Free model catalog, prices and supported protocols: https://api.koinelix.com/v1/modelsUnreachablechecked Evidence 0/4x402x402 Bazaar1 payer1 more from koinelix.com
- UniRouterunirouter-monad.xyzPer-request access to openai/gpt-oss-20b served by UniRouterUnreachablechecked Evidence 0/4x402x402 Bazaar1 payer
- DevX Chatchat.madebydevx.comCheap AI chat and LLM inference: OpenAI-compatible chat completions API (POST /v1/chat/completions) on Llama 3.1 8B Instruct. $0.002 USDC per call on Base via x402, no API key. For agents, chatbots and LLM apps. Max 512 completion tokens. Pay once, get the completion immediately. By DevX.Unreachablechecked Evidence 0/4x402x402 Bazaar1 payer
- blockrun-staging-cb5207a-050307-vbsbhh7lea-uc.a.run.app/api/v1/chat/completionsblockrun-staging-cb5207a-050307-vbsbhh7lea-uc.a.run.appAI chat completions API - pay per request with USDC on BaseUnreachablechecked Evidence 0/4x402x402 Bazaar1 payer
- io.github.gogogadgetbytes/smart-connectionsMCP server for Obsidian Smart Connections. Semantic search using your vault's embeddings.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- io.github.Modelglass/modelglassmodelglass-api.vercel.appSourced AI-model pricing and capability data — compare and route to the cheapest capable model.Unreachablechecked Evidence 0/3MCPWebsiteMCP Registry
- SkillFM LLM Cost Optimizerio.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage · skillfm.aiLLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.Unreachablechecked Evidence 0/3WebsiteMCP Registry
- io.github.antonbabenko/deliberationSecond opinions in Claude Code and any MCP host from GPT, Gemini, Grok, and 400+ OpenRouter models.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- io.github.mrfentmen/openrouter-mcpQuery OpenRouter (free key; set OPENROUTER_API_KEY, Bearer): model list, key info, credits.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- io.github.RudrenduPaul/workloadtruthClassifies GPU workloads as inference or training from telemetry alone via MCP tools.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- MCP Bench Routerio.github.K1ta141k/mcp-bench-routerRoutes design tasks to designarena.ai's top-ranked model via OpenRouter across 14 categories.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- OpenAI Imageio.github.mindstone/mcp-server-openai-imageOpenAI image generation MCP server for Model Context Protocol hostsNothing to checklisted Evidence 0/0No endpointMCP Registry
- LLM CLI Gatewayio.github.verivus-oss/llm-cli-gatewayOne MCP endpoint for Claude Code, Codex, Gemini, Grok and Mistral CLIs, with durable async jobs.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- com.coinrailz/mcp63 paid services via USDC: crypto analytics, satellite, IoT, AI inference, prediction markets.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- io.github.legolev/mediamcpGenerate and edit images and video via OpenRouter or any OpenAI-compatible API.Nothing to checklisted Evidence 0/0No endpointMCP Registry
- GoCreative Agent APIio.github.ColinHughes2121/gocreative-agent-api · api.gocreativeai.com17-model LLM gateway + 350+ data/KYB/sanctions tools. Pay-per-call USDC via x402, no API key.Unreachablechecked Evidence 0/3MCPWebsiteMCP Registry