Claude Fable 5

Frontier

AnthropicReasoningclaude-fable-5

Anthropic’s most capable model. Thinking always on — the gateway strips sampling parameters this model rejects.

Thinking always on; sampling parameters (temperature/top_p) are stripped by the gateway — Anthropic rejects them for this model. Anthropic requires 30-day data retention for this model (see provider docs).

Capabilities

Tool callingVisionReasoningJSON modePrompt cache

Recommended for

hardest reasoning problems
research
complex agentic work

Using this model through Conduix

Call it by its id, or let a routing alias pick it as part of a governed, cross-provider chain with automatic failover.

Direct model idclaude-fable-5

Reached by these routing aliases:

reasoning-bestprimary pick · Claude Fable 5 → GPT-5.5 → DeepSeek V4 Pro

Routing relationships are operational — chains adapt to provider availability and your org's policy — not a contractual guarantee that a specific model serves a given request.

Get started

Conduix is OpenAI-API-compatible — point any OpenAI SDK at https://api.conduix.ai/v1 and pass claude-fable-5 as the model.

from conduix import Conduix

client = Conduix(api_key="cx_live_YOUR_KEY")  # base URL is built in

response = client.chat.completions.create(
    model="claude-fable-5",
    messages=[{"role": "user", "content": "Hello, Conduix!"}],
)
print(response.choices[0].message.content)

Tool calling: Pass a tools array and the model calls your functions.
Vision: Accepts image inputs — add image_url parts to a message.
Reasoning: Reasons step-by-step — best for hard, multi-step problems.
JSON mode: Set response_format for guaranteed-valid JSON output.
Prompt cache: Repeated prompt context is billed at a reduced rate.

The response's x-conduix-model-served header tells you exactly which model answered. See the quickstart for keys, headers, and usage.