Anthropic: Claude Fable 5.1
Overview
Anthropic's model for demanding reasoning and long-horizon agentic work, Anthropic suggests it when Opus 5.5 at higher effort still falls short.
- Provider
Anthropic
- Modality
- Text and image
- Input
- text, image
- Output
- text
- Max output
- 128,000 tokens
- Weights
- Closed
- Supported parameters
- tools, structured_outputs, reasoningProvider's model page, checked .
- Distillable
- NoLicence or terms, checked .
- Tags
- reasoning, coding, agents, vision, long-context
Data policy
- Prompts go to
- Anthropic (global routing by default)
- Retention
- Not used for model training without express permission. Claude Fable 5.1 is a Covered Model that requires 30-day data retention and is not available under ZDR unless Anthropic expressly authorizes it
- Zero data retention
- Not offered
- Region
- Global by default, US-only inference via inference_geo at 1.1x pricing (Claude 4.6 and later)
- Policy
- Anthropic data policy
Summarised from the provider's published terms. The provider's own policy is what applies.
Where you can run it
How Claude Fable 5.1 can be deployed, bought and reached through Safeguard.
- Deployment
- Public cloudPrivate cloud
- Procurement
- Not published yet
- Inference regions
- 🇺🇸United StatesCloud provider's availability page, checked .
Closed weights stay with the provider, so this model runs in the provider's cloud, never on-prem.
Pricing
| Provider | Input / 1M tokens | Output / 1M tokens | Context |
|---|---|---|---|
| Anthropic | $10 | $50 | 1M |
- Notes
- Base price, full 1M context at standard rate. Cache hits $0.25/1M. Batch 50% off. US-only inference 1.1x.
- Source
- Anthropic pricing , last verified November 22, 2026
No markup on model usage: you pay the provider's list price.
API
OpenAI-compatible. Your API key and access to this model are set up for your workspace when you choose Use with Safeguard.
from openai import OpenAI
client = OpenAI(
base_url="https://api.safeguard.sh/gpt/v1",
api_key="SAFEGUARD_API_KEY",
)
response = client.chat.completions.create(
model="anthropic/claude-fable-5-1",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Base URL https://api.safeguard.sh/gpt/v1, model anthropic/claude-fable-5-1.
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.