Model comparison
Claude Fable 5.1 vs Claude Opus 5.5
ClaudeCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Claude Fable 5.1
Claude Opus 5.5
Included in Borg
At a glance
| Specification | Claude Fable 5.1 | Claude Opus 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Release | — | 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 | $10 input / $50 output | $4 input / $20 output |
| Borg | Included in Borg subscription | Included in Borg subscription |
AnthropicNot published by the vendor: release.
Measured 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)
Output tokens per second (whole turn)
| Metric | Claude Fable 5.1 | Claude Opus 5.5 |
|---|---|---|
| Time to first token (gateway proxy) p50 | 6015 ms (2192 samples) | 2946 ms (75410 samples) |
| Tokens per second (end to end) p50 | 55.9 output tokens per second (7156 samples) | 60 output tokens per second (203387 samples) |
| Request success rate | 99.9% (6283 samples) | 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 Fable 5.1: 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.
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
Vendor benchmarks
Vendor-reported scores may use different settings; do not treat them as a controlled head-to-head test.
How to choose
Claude Fable 5.1 is listed for long-horizon coding agents tackling difficult repositories, whereas Claude Opus 5.5 is listed for long-running agentic coding across repositories. Choosing between Claude Fable 5.1 and Claude Opus 5.5 requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Claude Fable 5.1 | 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 | Not published | 2026-09-22 Vendor source |
| API price input / 1M | 10 | 4 Lower listed rate |
| API price output / 1M | 50 | 20 Lower listed rate |
| Time to first token (gateway proxy) | 6015 ms (2192 samples) | 2946 ms (75410 samples) Lower median |
| Output tokens per second (whole turn) | 55.9 output tokens/s (whole turn) (7156 samples) | 60 output tokens/s (whole turn) (203387 samples) Higher measured rate |
| Request success | 99.9% (6283 samples) | Not published |
| Coding bench | Not published | Not published |
FAQ
How do Claude Fable 5.1 and Claude Opus 5.5 compare for coding?
Claude Fable 5.1 has a Borg coding benchmark of not published; Claude Opus 5.5 has not published. The Claude Fable 5.1–Claude Opus 5.5 coding comparison cannot establish an overall winner from this small test alone.
How quickly do Claude Fable 5.1 and Claude Opus 5.5 start responding on Borg?
Borg median first response for Claude Fable 5.1 is 6,015 ms; for Claude Opus 5.5 it is 2,946 ms. The Claude Fable 5.1–Claude Opus 5.5 gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Claude Fable 5.1 and Claude Opus 5.5?
The listed API rate for Claude Fable 5.1 is $10 input / $50 output per 1M tokens; for Claude Opus 5.5 it is $4 input / $20 output per 1M tokens. Neither Claude Fable 5.1 nor Claude Opus 5.5 has its Borg subscription charge represented by those provider API rates. Claude Fable 5.1 vendor source · Claude Opus 5.5 vendor source
Gemini