Google tells you what exists. Faceabot tells you what holds up.
x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.
Package npm :@nodeproxy/tokensqueezer · website · measurements and detailsCompress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.
Package pypi :token-compressor-mcp · website · measurements and detailsPremium agentic endpoint for brotli-prompt-compressor-mcp.
MCP endpoint :https://api.m2mcent.com/brotli-prompt-compressor-mcp/sse · measurements and detailsPremium agentic endpoint for draco-mesh-compressor-mcp.
MCP endpoint :https://api.m2mcent.com/draco-mesh-compressor-mcp/sse · measurements and detailsLLM token optimization gateway implementing semantic pruning.
MCP endpoint :https://token-diet-mcp.vercel.app/api/mcp · measurements and detailsCompare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.
MCP endpoint :https://llmabacus.com/api/mcp · website · measurements and detailsMeasured latency, time to first token and uptime for ~45 AI inference APIs, by region.
MCP endpoint :https://llmlatency.dev/mcp · website · measurements and detailsRead-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.
MCP endpoint :https://elgadmisijrfowuujcmu.supabase.co/functions/v1/mcp · website · measurements and detailsToken cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.
Package npm :@comparedge/llm-cost-mcp · website · measurements and detailsHosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
MCP endpoint :https://mcp.guffeyholdings.com/TokenOracle · website · measurements and detailsGoogle-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f
MCP endpoint :https://anthropic-google-auth-oauthlib-mc-70ac16.getvda.ai/mcp · website · measurements and detailsCuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.
Package pypi :xelektron-token-enhancer · website · measurements and detailsLLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Package npm :@skillfm/llm-cost-optimizer-mcp · website · measurements and detailsNegotiation math engine. Pareto frontier, counteroffer generation, zero LLM tokens.
MCP endpoint :https://zopaf-mcp-production.up.railway.app/mcp · website · measurements and detailsCut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.
Package npm :mcp-token-optimizer · website · measurements and detailsLive LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.
MCP endpoint :https://modelpricewatch.com/mcp · website · measurements and detailsA paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
MCP endpoint :https://rtkcontext.clauxel.com/mcp · website · measurements and detailsToken counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Package npm :llm-cost-estimator-mcp · website · measurements and detailsSelf-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.
MCP endpoint :https://mcp.clusteragent.dev/mcp · website · measurements and detailsMCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens
Package npm :claude-token-saver-mcp · website · measurements and detailsAI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt
Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Open reliability data · Add Faceabot to your AI · Help · Privacy · Terms