Fable 5.5 API: Is It Available?

Model IDs that work today

Three-minute setup

Full docs: docs.omniakey.com — Anthropic protocol on the bare host, OpenAI protocol at /v1/chat/completions; the same key also covers OpenAI and Gemini models.

Python

from anthropic import Anthropic

client = Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://api.omniakey.com",  # drop this line for the official endpoint
)

message = client.messages.create(
    model="claude-fable-5-1",
    max_tokens=2048,
    messages=[{"role": "user", "content": "Explain Fable 5.1 in one sentence"}],
)
print(message.content[0].text)

Node.js

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.omniakey.com", // drop for the official endpoint
});

const msg = await client.messages.create({
  model: "claude-fable-5-1",
  max_tokens: 2048,
  messages: [{ role: "user", content: "Hello, Fable 5.1" }],
});
console.log(msg.content[0].text);

cURL

curl https://api.omniakey.com/v1/messages \
  -H "x-api-key: $YOUR_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-fable-5-1",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

How to get a Fable API key

Official: sign up at Claude Console, add a card, generate a key on the API Keys page. OmniaKey: sign up → top up (balance never expires; unused balance refundable within 30 days) → generate a key, then point base_url at it in the setup above.

Pricing at a glance

USD per million tokens. Cache writes, paid tools, taxes and regional routing are separate. Verify live rates before approving a production budget.

Safety fallback: the gotcha to know

• Log the fallback flag — monitor your downgrade rate, especially for security or bio products.
• Budget a blended rate for high-sensitivity domains.
• Handle quality fallbacks — flows that depend on 1M context should detect downgrades and decide whether to retry.

Engineering notes

• Stream long jobs. Non-streaming calls can hit default client timeouts on long-horizon work — set HTTP timeouts in the 10-minute range.
• Lean on prompt caching. Fable 5.1 cut the cache-read rate to $0.25/M ($0.07/M on OmniaKey). Long system prompts and RAG context belong in cache.
• Reserve Fable for hard work. For short, well-defined tasks, swap the model string to claude-opus-5-5 or claude-sonnet-5-5 — same code.
• Pin the version. Keep the model configurable so a future Fable release is a one-line change plus a fresh eval.