Anthropic · in Borg

Claude Fable 5.1

Claude Fable 5.1 is the demanding-reasoning tier of Anthropic’s 5.1 generation, offered more broadly than its safeguarded Mythos counterpart.

Reasoning1,000,000 tokenstext, image

1,000,000 tokensContext window

6015 msMedian time to first token (gateway proxy)

55.9Output tokens per second (whole turn)

99.9%Request success

$10 / $50Vendor API price in / out · per 1M

Included in Borg

Download Borg Borg for Business

At a glance

Specification	Value
Provider	Anthropic
Family	Claude
Context window	1,000,000 tokens Vendor source
Input modalities	text, image
Output modalities	text
Reasoning	Yes
Open weights	No
Knowledge cutoff	2026-06 Vendor source
Borg lane ids	`claude-fable-5-1`
Median time to first token (gateway proxy) on Borg	6015 ms
Median tokens per second (end to end) on Borg	55.9 output tokens per second

Not published by the vendor: release date, thinking modes, fusion roles.

What Claude Fable 5.1 is good for

Claude Fable 5.1 is the demanding-reasoning tier of Anthropic’s 5.1 generation, offered more broadly than its safeguarded Mythos counterpart. It extends Fable 5 for long-horizon agentic coding, multistep research, and producing documents, spreadsheets, and slides. Unlike the faster and less expensive Opus 5.5, this is the model to try when difficult tasks still fail at higher Opus effort; it is also substantially more costly than Sonnet 5.5 and Haiku 4.5. Its adaptive thinking is always on, making it a poor choice for trivial, latency-sensitive requests but useful when a task needs sustained planning and careful revision. Borg includes Fable in the subscription: Borg Fusion can route demanding work to it, or you can select its lane directly to keep a challenging workflow on this model.

long-horizon coding agents tackling difficult repositories
multistep research and synthesis
complex spreadsheet and slide production
hard reasoning tasks that defeat cheaper models

How Borg uses it

Claude Fable 5.1 is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.

model: "claude-fable-5-1"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	6015 ms	28596 ms	2192
Tokens per second (end to end)	55.9 output tokens per second	88 output tokens per second	7156
Request success rate	99.9%	—	6283

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Claude Fable 5.16015 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Claude Fable 5.155.9 tokens/s

Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate

Share of requests Borg completed successfully, excluding requests the client cancelled.

Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.

Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 7924 requests. Minimum 100 samples per published request metric.

Benchmarks

Benchmark	Vendor-reported score	Source
Terminal-Bench-Science 0.1	52.6%	Vendor source
Terminal-Bench 4.0	55.8%	Vendor source
OSWorld 2.0 (partial)	77.9%	Vendor source
Humanity’s Last Exam (no tools)	60.9%	Vendor source
CursorBench 3.2.0	73.4%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $10 input / $50 output per 1M tokens. Vendor price source.

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Claude Fable 5.1?

Claude Fable 5.1 is listed in Borg's subscription catalog as claude-fable-5-1. Claude Fable 5.1 is the demanding-reasoning tier of Anthropic’s 5.1 generation, offered more broadly than its safeguarded Mythos counterpart.

Is Claude Fable 5.1 in Borg?

Yes. Claude Fable 5.1 is listed in Borg's subscription catalog under the lane claude-fable-5-1. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.

What context window does Claude Fable 5.1 have?

The published context window is 1,000,000 tokens. Consult the cited sources for details and current limits. Vendor source

Is Claude Fable 5.1 good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include long-horizon coding agents tackling difficult repositories, multistep research and synthesis, complex spreadsheet and slide production, hard reasoning tasks that defeat cheaper models. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Claude Fable 5.1 on Borg?