Claude API key

A Claude API key authenticates your calls to Anthropic's Claude models. You can get one directly from the Anthropic Console, or use a single sk-kunavo- key that reaches Claude — via the OpenAI SDK or the native Messages API — alongside every other model.

Option A — a key direct from the Anthropic Console

1. Go to console.anthropic.com and sign in.
2. Open Settings → API keys → Create Key. Keys look like sk-ant-....
3. Add a payment method under Billing — there is no free tier.

This is the right path if Claude is the only model you will ever call. If you also use Gemini, GPT, image or video models, you would manage a separate key, SDK and invoice per provider.

Option B — one Kunavo key for Claude and everything else

Kunavo fronts Claude behind both an OpenAI-compatible API and the native Anthropic Messages API. One sk-kunavo- key reaches Claude and every other model, with a single Stripe-billed balance.

1. Create a Kunavo account — you get $2 of free credit.
2. Generate a key at /app/keys. It is shown once; store it in an environment variable.
3. Point the OpenAI SDK at https://api.kunavo.com/v1 and call a Claude slug.

Call Claude with Python

Keep the official OpenAI SDK. Change base_url and the model name — nothing else.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["KUNAVO_API_KEY"],
    base_url="https://api.kunavo.com/v1",  # the only line that changes
)

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "Explain quicksort in one paragraph."}],
)
print(resp.choices[0].message.content)

Call Claude with Node.js

import OpenAI from "openai";

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

const resp = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [{ role: "user", content: "Explain quicksort in one paragraph." }],
});
console.log(resp.choices[0].message.content);

Or call it with curl

curl https://api.kunavo.com/v1/chat/completions \
  -H "Authorization: Bearer $KUNAVO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "Hello, Claude"}]
  }'

Which Claude model to use

• claude-haiku-4-5 — cheapest and fastest; great for high-volume classification and support.
• claude-sonnet-4-6 — the balanced default for most reasoning, RAG and coding.
• claude-opus-4-7 — the heaviest reasoner, for the hardest problems and long context.

Troubleshooting

Security checklist

• Never expose a key client-side. Always proxy through your own server.
• Use one key per project or environment so a leak can be revoked without taking down everything else.
• Rotate quarterly. Kunavo allows multiple live keys for a clean overlap.

FAQ

Where to go next

• Messages API reference (native Anthropic shape)
• Claude API pricing 2026
• Quickstart — your first request in 60 seconds