Quickstarts

From API key to first answer

Call Redrob with the official OpenAI SDKs for Python and JavaScript, or with curl: first answer, streaming, and answers in the language the question was asked in.

1. Get an API key

Create a workspace, or sign in to one you already have.
Open API keys and create a key.
Copy it there and then. The full key is shown once and never again.
Keep it server-side as REDROB_API_KEY.

2. Point the OpenAI SDK at Redrob

The completion API speaks OpenAI’s chat completions protocol, so the official SDKs work unchanged. There is no Redrob package to install: set the base URL and the key.

Python

# pip install openai
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["REDROB_API_KEY"],
    base_url="https://console.redrob.ai/api/backend/v1",
)

answer = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "What is a robot?"}],
)

print(answer.choices[0].message.content)

JavaScript and TypeScript

// npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.REDROB_API_KEY,
  baseURL: "https://console.redrob.ai/api/backend/v1",
});

const answer = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "What is a robot?" }],
});

console.log(answer.choices[0].message.content);

Anything built on those SDKs works the same way - LangChain, LlamaIndex, the Vercel AI SDK - wherever an OpenAI-compatible base URL can be configured.

Or use curl

Worth doing once to confirm the key before any application code is involved.

curl

export REDROB_API_KEY="rrk_…"

curl https://console.redrob.ai/api/backend/v1/chat/completions \
  -H "Authorization: Bearer $REDROB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{ "role": "user", "content": "What is a robot?" }]
  }'

3. Work in more than one language

A completion needs nothing special for this: ask in Tamil and the answer comes back in Tamil. Translating is a separate call, so you decide what gets translated and pay for exactly that, rather than every non-English request quietly costing two.

Python

import httpx

# The completion itself needs nothing special: ask in Tamil, get Tamil back.
answer = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "தமிழில் சென்னையைப் பற்றி சொல்லுங்கள்."}],
)

# Translate when you want to, and pay for just that.
english = httpx.post(
    "https://console.redrob.ai/api/backend/v1/translate",
    headers={"Authorization": f"Bearer {REDROB_API_KEY}"},
    json={
        "input": answer.choices[0].message.content,
        "sourceLanguage": "auto",
        "targetLanguage": "en",
    },
).json()

print(english["text"])

JavaScript and TypeScript

const answer = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "हिंदी में जयपुर के बारे में बताइए।" }],
});

const translated = await fetch(
  "https://console.redrob.ai/api/backend/v1/translate",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.REDROB_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      input: answer.choices[0].message.content,
      sourceLanguage: "auto",
      targetLanguage: "en",
    }),
  }
).then(r => r.json());

Fifteen languages: en, ko, hi, bn, pa, gu, or, ta, te, kn, ml, ur, mr, ne, as. Pass auto as the source and the language is detected by script, which costs nothing.

4. Stream the answer

Python

stream = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Explain the Indian monsoon."}],
    stream=True,
)

for chunk in stream:
    piece = chunk.choices[0].delta.content
    if piece:
        print(piece, end="", flush=True)

JavaScript and TypeScript

const stream = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Explain the Indian monsoon." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

One caveat worth knowing: an answer that has to be translated back into the language it was asked in arrives as a single chunk, because there is nothing to show until the whole answer exists.

Where to go next

Every field and status code is in the API reference.
Try prompts without writing code in the playground.
Issue a key per environment in API keys, so one can be revoked without taking the others down.
Watch tokens, cost, and latency per call in request logs.