Model comparison
Claude Opus 4.6 vs Claude Opus 5.5
ClaudeCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Claude Opus 4.6
Claude Opus 5.5
Included in Borg
At a glance
| Specification | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Release | 2026-02-05 Vendor source | 2026-09-22 Vendor source |
| Context | 1,000,000 tokens Vendor source | 1,000,000 tokens Vendor source |
| Modalities | Input: text, image; output: text | Input: text, image; output: text |
| Reasoning / thinking modes | Yes / Not published | Yes / Not published |
| Open weights | No | No |
| Vendor API list price / 1M tokens | $5 input / $25 output | $4 input / $20 output |
| Borg | Included in Borg subscription | Included in Borg subscription |
AnthropicMeasured on Borg
Metrics are not directly comparable to vendor benchmark claims. Models served different requests; this is observed gateway traffic, not a controlled head-to-head test.
Time to first token (gateway proxy)
No published measurement for this model.
Output tokens per second (whole turn)
| Metric | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| Time to first token (gateway proxy) p50 | Not published | 2946 ms (75410 samples) |
| Tokens per second (end to end) p50 | 35.5 output tokens per second (153 samples) | 60 output tokens per second (203387 samples) |
| Request success rate | Not published | Not published |
| Coding bench pass rate | Not published | Not published |
Measurement window, samples and methodology
The fleet reference is the median of published model medians, not a request-weighted result. Prompt lengths, reasoning settings and traffic differ between models.
Claude Opus 4.6: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 191 requests. Minimum 100 samples per published request metric.
Claude Opus 5.5: 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.
Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.
- 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
How to choose
Claude Opus 4.6 is listed for maintaining workflows calibrated to Opus 4.6, whereas Claude Opus 5.5 is listed for long-running agentic coding across repositories. Choosing between Claude Opus 4.6 and Claude Opus 5.5 requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Claude Opus 4.6 | Claude Opus 5.5 |
|---|---|---|
| Context window | 1,000,000 tokens Vendor source | 1,000,000 tokens Vendor source |
| Reasoning modes | Yes / Not published | Yes / Not published |
| Release date | 2026-02-05 Vendor source | 2026-09-22 Vendor source |
| API price input / 1M | 5 | 4 Lower listed rate |
| API price output / 1M | 25 | 20 Lower listed rate |
| Time to first token (gateway proxy) | Not published | 2946 ms (75410 samples) |
| Output tokens per second (whole turn) | 35.5 output tokens/s (whole turn) (153 samples) | 60 output tokens/s (whole turn) (203387 samples) Higher measured rate |
| Request success | Not published | Not published |
| Coding bench | Not published | Not published |
FAQ
How do Claude Opus 4.6 and Claude Opus 5.5 compare for coding?
Claude Opus 4.6 has a Borg coding benchmark of not published; Claude Opus 5.5 has not published. The Claude Opus 4.6–Claude Opus 5.5 coding comparison cannot establish an overall winner from this small test alone.
How quickly do Claude Opus 4.6 and Claude Opus 5.5 start responding on Borg?
Borg median first response for Claude Opus 4.6 is not published; for Claude Opus 5.5 it is 2,946 ms. The Claude Opus 4.6–Claude Opus 5.5 gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Claude Opus 4.6 and Claude Opus 5.5?
The listed API rate for Claude Opus 4.6 is $5 input / $25 output per 1M tokens; for Claude Opus 5.5 it is $4 input / $20 output per 1M tokens. Neither Claude Opus 4.6 nor Claude Opus 5.5 has its Borg subscription charge represented by those provider API rates. Claude Opus 4.6 vendor source · Claude Opus 5.5 vendor source