Anthropic · in Borg

Claude Sonnet 5.5

Claude Sonnet 5.5 is Anthropic’s faster, lower-priced 5.5 model for work that is substantial but well scoped.

Reasoning1,000,000 tokenstext, image

1,000,000 tokensContext window

2640 msMedian time to first token (gateway proxy)

76.7Output tokens per second (whole turn)

$2 / $10Vendor API price in / out · per 1M

Included in Borg

Download Borg Borg for Business

At a glance

Specification	Value
Provider	Anthropic
Family	Claude
Release date	2026-09-28 Vendor source
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-sonnet-5-5`
Versions in Borg	Claude Sonnet 4.6 · Claude Sonnet 5.5
Median time to first token (gateway proxy) on Borg	2640 ms
Median tokens per second (end to end) on Borg	76.7 output tokens per second

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

What Claude Sonnet 5.5 is good for

Claude Sonnet 5.5 is Anthropic’s faster, lower-priced 5.5 model for work that is substantial but well scoped. Compared with Sonnet 5 it improves coding and everyday productivity; compared with Opus 5.5 it favors speed and price over sustained, open-ended judgment. It can fix bugs, handle structured computer-use tasks, and create polished documents, spreadsheets, slides, and design-oriented drafts. Adaptive thinking is available, but the model can also avoid up-front thinking for applications that need a quicker path to an answer. Its context capacity matches the larger models, so a long input alone need not force an Opus or Fable choice. Borg includes Sonnet 5.5 in the subscription; Borg Fusion can choose it for balanced tasks, or you can select its lane directly for predictable turnaround.

well-scoped bug fixes and code reviews
document and slide drafting with revisions
computer-use and structured agent tasks
fast analysis of lengthy source material

How Borg uses it

Claude Sonnet 5.5 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-sonnet-5-5"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	2640 ms	27817 ms	35971
Tokens per second (end to end)	76.7 output tokens per second	147.3 output tokens per second	86888

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Claude Sonnet 5.52640 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Claude Sonnet 5.576.7 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

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; 94296 requests. Minimum 100 samples per published request metric.

Benchmarks

Benchmark	Vendor-reported score	Source
Terminal-Bench 4.0	70.6%	Vendor source
CursorBench 4.0	55.5%	Vendor source
Humanity’s Last Exam (with tools)	64.5%	Vendor source
OSWorld 2.1 (partial)	80.1%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $2 input / $10 output per 1M tokens. Vendor price source.

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Claude Sonnet 5.5?

Claude Sonnet 5.5 is listed in Borg's subscription catalog as claude-sonnet-5-5. Claude Sonnet 5.5 is Anthropic’s faster, lower-priced 5.5 model for work that is substantial but well scoped.

Is Claude Sonnet 5.5 in Borg?

Yes. Claude Sonnet 5.5 is listed in Borg's subscription catalog under the lane claude-sonnet-5-5. 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 Sonnet 5.5 have?

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

Is Claude Sonnet 5.5 good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include well-scoped bug fixes and code reviews, document and slide drafting with revisions, computer-use and structured agent tasks, fast analysis of lengthy source material. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Claude Sonnet 5.5 on Borg?