Anthropic · in Borg

Claude Opus 5.5

Claude Opus 5.5 launched as the first member of Anthropic’s 5.5 family.

Reasoning1,000,000 tokenstext, image

1,000,000 tokensContext window

2946 msMedian time to first token (gateway proxy)

60Output tokens per second (whole turn)

$4 / $20Vendor 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	2026-09-22 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-opus-5-5`
Versions in Borg	Claude Opus 4.6 · Claude Opus 5.5
Median time to first token (gateway proxy) on Borg	2946 ms
Median tokens per second (end to end) on Borg	60 output tokens per second

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

What Claude Opus 5.5 is good for

Claude Opus 5.5 launched as the first member of Anthropic’s 5.5 family. It targets long-running coding agents and involved knowledge work, with adaptive thinking that cannot be disabled. Anthropic positions it as the default starting point for most work: it approaches the performance of the more expensive Fable 5.1 on many tasks, while Sonnet 5.5 is the faster, cheaper pick for well-scoped everyday requests. Its large context and output capacity make it practical for sustained tool-using sessions, repo-level changes, and document-heavy projects. For brief classification or simple edits, the extra spend compared with Sonnet or Haiku is harder to justify. Borg includes Opus 5.5 in the subscription; Borg Fusion can route complex work to it, while selecting its lane directly gives you a consistent model for extended sessions.

long-running agentic coding across repositories
multi-document research and analysis
complex professional writing and revision
tool-heavy workflows requiring careful judgment

How Borg uses it

Claude Opus 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-opus-5-5"

Measured on Borg

Metric	Median	95th percentile	Samples
Time to first token (gateway proxy)	2946 ms	26356 ms	75410
Tokens per second (end to end)	60 output tokens per second	105.1 output tokens per second	203387

Time to first token (gateway proxy)

Lower is fasterFleet median 3971.5 ms

Claude Opus 5.52946 ms

Output tokens per second (whole turn)

Higher is fasterFleet median 31.9 tokens/s

Claude Opus 5.560 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; 220887 requests. Minimum 100 samples per published request metric.

Benchmarks

Benchmark	Vendor-reported score	Source
Terminal-Bench 4.0	66.4%	Vendor source
FrontierCode v1.1 (Main)	54.4%	Vendor source
CursorBench 4.0	57.8%	Vendor source
AutomationBench	40.0%	Vendor source
Humanity’s Last Exam (with tools)	67.7%	Vendor source

Pricing

Included in Borg subscription. Vendor API list price: $4 input / $20 output per 1M tokens. Vendor price source.

Compare subscription and API pricing · Cost Savings Calculator

FAQ

What is Claude Opus 5.5?

Claude Opus 5.5 is listed in Borg's subscription catalog as claude-opus-5-5. Claude Opus 5.5 launched as the first member of Anthropic’s 5.5 family.

Is Claude Opus 5.5 in Borg?

Yes. Claude Opus 5.5 is listed in Borg's subscription catalog under the lane claude-opus-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 Opus 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 Opus 5.5 good for coding?

Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include long-running agentic coding across repositories, multi-document research and analysis, complex professional writing and revision, tool-heavy workflows requiring careful judgment. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.

How fast is Claude Opus 5.5 on Borg?