Every model,
refracted through
one endpoint.

from openai import OpenAI

client = OpenAI(
    base_url="https://prism402.com/v1",
    api_key="prism_sk_...",
)

reply = client.chat.completions.create(
    model="kimi-k2.6",
    messages=[{"role": "user", "content": "What is Robinhood Chain?"}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://prism402.com/v1",
  apiKey: process.env.PRISM_KEY,
});

const reply = await client.chat.completions.create({
  model: "glm-5.3",
  messages: [{ role: "user", content: "What is Robinhood Chain?" }],
});

# 1. Ask. No key: the answer is 402 with the price.
curl -i https://prism402.com/v1/chat/completions \
  -H "content-type: application/json" \
  -d '{"model":"gpt-oss-120b","max_tokens":800,
       "messages":[{"role":"user","content":"hi"}]}'

# 2. Sign the USDG authorization in PAYMENT-REQUIRED,
#    resend with PAYMENT-SIGNATURE. Any x402 v2 client
#    (e.g. @x402/fetch) does both steps for you.

# Any MCP client: list_models, chat, trench_scan.
# Pays with a prepaid key, or a wallet via x402.
claude mcp add prism402 \
  -e PRISM402_API_KEY=prism_sk_... \
  -- npx -y prism402

# Claude Desktop / Cursor: mcpServers.prism402
{ "command": "npx", "args": ["-y", "prism402"] }