We shipped an MCP server.
Every AI model behind one MCP endpoint. Text, images, video.
Pay per request with Bitcoin or USDC.
Because you shouldn't need 5 API keys and 3 billing dashboards to use AI.
Docs:
Not your node, not your service.
llm402.ai now runs its own Lightning nodes.
No custodial middleman.
We fix problems. We don't wait on them.
#Bitcoin #Lightning #L402 #Cashu #AI #LLM
You shouldn't need a Google account to generate a video.
llm402.ai now serves 20 video models and 41+ image models. Sora 2, Veo 3, Kling 2.1, FLUX 2, Imagen 4, GPT-5 Image, and more.
Pay per request with Lightning, USDC on Base, Cashu, or prepaid balance.
llm402.ai β‘οΈ
#Bitcoin #Lightning #L402 #x402 #AI #LLM
Been heads down building.
Payment: four rails, no accounts needed.
β‘ Lightning (L402)
π₯ Cashu ecash
π² USDC on Base (x402)
π Bearer token (OpenAI SDK drop-in)
Any client, any rail.
Advanced routing engine β health-aware, cost-aware, auto-steers to the best model for your prompt.
300+ models including all frontier.
One line to switch from OpenAI:
client = OpenAI(base_url="api.bestpath.ai/v1", api_key="bal...")
Shipping more soon..
llm402.ai
#Bitcoin #Lightning #L402 #Cashu #AI
Been heads down building.
Payment: four rails, no accounts needed.
β‘ Lightning (L402)
π₯ Cashu ecash
π² USDC on Base (x402)
π Bearer token (OpenAI SDK drop-in)
Any client, any rail.
Advanced routing engine β health-aware, cost-aware, auto-steers to the best model for your prompt.
300+ models including all frontier.
One line to switch from OpenAI:
client = OpenAI(base_url="api.bestpath.ai/v1", api_key="bal...")
Shipping more soon..
llm402.ai
llm402.ai updates β‘
β OpenAI + Ollama compatible streaming (SSE + NDJSON)
β NWC-first invoicing (faster payments, LNURL fallback)
β CJK-aware pricing (fair tokenization for all languages)
β health checks every 60s β you never pay for a dead model
β context validation before invoice β no wasted sats
β dynamic pricing syncs with BTC price every 60s
β playground is live! β temperature, top_p, top_k, repetition penalty, min_p, seed, all exposed. full control over inference.
32 models. No accounts. No API keys. Just sats.
Pay-per-prompt LLM access over LightningΒ
I built an LLM API that only accepts Lightning payments (L402)
Been working on this for a while and figured I'd share since it's live and working.
32 LLM models (DeepSeek-R1, Llama, Qwen, Mistral, etc.) accessible via L402. No API keys, no accounts, no email signup. Just pay a Lightning invoice and get inference.
How it works:
- Send a request (OpenAI-compatible or Ollama format)
- Get back a 402 with a Lightning invoice + macaroon Pay the invoice Resend with the preimage - get your response
- Pricing is dynamic - calculated per-request based on model cost, input size, and max output tokens.
- Converted to sats using live BTC price. Cheapest requests are ~10 sats.
Built for agents - see curl examples on the site. Works with lnget from Lightning Labs for full L402 flow automation.
Also listed inΒ 402index.
If there are other models you'd want to see, features that would make this more useful, let me know. Happy to hear what people think.