Open models

RightNow AI Open models Updated 2026-11-14

The open models API serves hosted open-weight models through chat-completions-compatible and Messages-compatible protocols. One workspace API key reaches them all, and credits pay for usage.

two protocols, one key

Text

  chat completions        Messages
  /v1/chat/completions    /v1/messages
           │                   │
           └─────────┬─────────┘
                     │ one workspace key
                     ▼
╔══════════════════════════════════════╗
║ one base URL         the open models ║
╚════════════════════╤═════════════════╝
                     │ usage
                     ▼
┌──────────────────────────────────────┐
│ one credit balance   █████████░░░░░░ │
└──────────────────────────────────────┘

Illustration of one workspace key reaching the open models through two protocols.

Connection	Value
API base	`https://api.rightnowai.co/v1`
Chat completions	`POST /v1/chat/completions`
Messages	`POST /v1/messages`
Workspace key	`rp_...`
Process variable	`RIGHTNOW_API_KEY`

The RightNow decision model has its own docs.

Call a hosted model

Set the base URL to https://api.rightnowai.co/v1, use a workspace API key and pass a model id.

Replace MODEL_ID with an available id from Open models; read current capabilities, limits and prices from GET /v1/models.

TypeScript

import OpenAI from "openai";

// Server side only: never expose this key in browser code.
const client = new OpenAI({
  baseURL: "https://api.rightnowai.co/v1",
  apiKey: process.env.RIGHTNOW_API_KEY,
});
const response = await client.chat.completions.create({
  model: "MODEL_ID",
  messages: [{ role: "user", content: "Write a TypeScript retry helper." }],
  max_tokens: 16384,
});
console.log(response.choices[0]?.message?.content);

GET /v1/models is the authoritative list of hosted chat models. It also reports when one is temporarily paused.

Call an open model

Key, base URL, first call.

Compatible clients

Change the base URL, the key and the model id in the client you already use.

Limits

Request, concurrency and token limits by operation.

Set up a coding agent

Copy one prompt. Your coding agent sets up the open models API for you.

Pricing, access and help

Pricing and credits

Pay as you go and USD 5 minimum top-up.

Account and access

Troubleshooting

401, 402, 403, 429, 503 and what to do about each.