Claude Fable 5 High

High-effort text test · Uses high reasoning with room for the required 4,096-token thinking budget. This test does not reproduce the Arena benchmark.

Claude Fable 5 High · Python

import requests

response = requests.post(
    url="https://api.roten-ai.com/v1/responses",
    headers={
        "Authorization": "Bearer YOUR_ROTEN_API_KEY",
    },
    json={
        "model": "claude-fable-5",
        "input": "Write one short welcome sentence for a developer starting with Roten AI.",
        "reasoning": {
            "effort": "high"
        },
        "max_output_tokens": 4608
    },
    timeout=180,
)

print(response.json())
response.raise_for_status()

Claude Fable 5 High · cURL

curl --fail-with-body 'https://api.roten-ai.com/v1/responses' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_ROTEN_API_KEY' \
  -d '{
  "model": "claude-fable-5",
  "input": "Write one short welcome sentence for a developer starting with Roten AI.",
  "reasoning": {
    "effort": "high"
  },
  "max_output_tokens": 4608
}'

Python requires requests: install once with python3 -m pip install requests. cURL examples run directly in your terminal.

Consider an alternative.

Compare its input formats, capabilities and prices.

GLM-5.3 Flash

Z.ai

Available

Alternative cost candidate for text. Alternative cost candidate for coding.

$0.15 input / $0.50 output · per 1M tokens

View Model

Kimi K2.6

Moonshot AI

Available

Alternative cost candidate for documents.

Documents use extracted text, not native PDF uploads.

$0.665 input / $2.80 output · per 1M tokens

View Model

Built for production

Running AI at scale?

Talk to us about volume pricing, model selection and migration.

Talk to Sales