ssimplifi-prism — Node SDK for Prism

npm install ssimplifi-prism

Quick start

import { Prism } from "ssimplifi-prism";

const client = new Prism({ apiKey: process.env.PRISM_API_KEY! });

const response = await client.chat.completions.create({
  messages: [{ role: "user", content: "What's the capital of Australia?" }],
  mode: "balanced",
});
console.log(response.choices[0].message.content);

That's it. The SDK extends the official OpenAI Node SDK, pointed at Prism's base URL. Everything you already know about openai — streaming, retries, response shape — works identically.

Prism-specific kwargs

| Field | Header | What it does | |---|---|---| | mode: "eco" \| "balanced" \| "sport" | X-Prism-Mode | Quality/cost mode for auto-routing | | model_prefer: "claude-sonnet" | X-Prism-Model-Prefer | Force a specific model | | session_id: "user-abc" | X-Prism-Session | Multi-turn memory | | cache: "off" \| "exact" \| "semantic" | X-Prism-Cache | Cache behavior for this request | | request_tags: { feature: "search" } | X-Prism-Request-Tags | Attribution tags for usage breakdown |

// Multi-turn chat with session memory
await client.chat.completions.create({
  messages: [{ role: "user", content: "Remember: my name is Ravi" }],
  session_id: "user-abc",
});

// Next call — no need to resend history
const r = await client.chat.completions.create({
  messages: [{ role: "user", content: "What's my name?" }],
  session_id: "user-abc",
});
console.log(r.choices[0].message.content);  // "Your name is Ravi."

Admin methods (Pro/Team tier)

// Live model catalog
const catalog = await client.models.list({ provider: "groq" });
console.log(catalog.summary);

// Your usage
console.log(await client.usage.summary({ days: 7 }));

// Cache stats
console.log(await client.cache.stats({ days: 7 }));

// API keys
console.log(await client.keys.list());
const newKey = await client.keys.create({ name: "staging-app" });
console.log(newKey.key);  // full secret shown ONCE
await client.keys.revoke("key-id-from-list");

// Identity + balance
console.log(await client.whoami());
console.log(await client.balance());

Drop-in replacement for plain OpenAI

// Before
import OpenAI from "openai";
const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

// After
import { Prism } from "ssimplifi-prism";
const client = new Prism({ apiKey: process.env.PRISM_API_KEY! });

Every client.chat.completions.create(...) call you already wrote continues to work. Add mode: and you've got auto-routing + caching + multi-provider failover.

Compatibility

• Node 18+
• Builds on openai@^4.50.0
• Tied to the Prism backend /v1/ major version — SDK 1.x works with any backend 1.x.

License

Apache-2.0