Le catalogue réel des outils pour IA

x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.

Compress prompts 40-60% using local LLM + embedding validation. Preserves all conditionals.

Premium agentic endpoint for brotli-prompt-compressor-mcp.

Premium agentic endpoint for draco-mesh-compressor-mcp.

LLM token optimization gateway implementing semantic pruning.

Compare up-to-date pricing for 40+ LLMs (incl. Chinese) & estimate cost from tokens. EN/zh.

Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.

Token cost math for LLM API calls: verified per-1M-token rates for 69 models, 17 providers.

Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

Cuts AI web-fetching costs up to 99.9% by stripping page junk before it reaches your LLM.

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.

Negotiation math engine. Pareto frontier, counteroffer generation, zero LLM tokens.

Cut LLM token costs: count tokens, estimate cost, slim prompts, and pick the cheapest capable model.

Live LLM API pricing: token prices, comparisons, cheapest-model lookups. No key required.

A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log

Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.

Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.

MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens