Model comparison
Borg Fusion vs Borg Fusion Coding
Compare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Borg Fusion
Borg Fusion Coding
Included in Borg
At a glance
| Specification | Borg Fusion | Borg Fusion Coding |
|---|---|---|
| Provider | Borg | Borg |
| Reasoning / thinking modes | Not published / low, medium, high | Not published / low, medium, high, max |
| Borg | Included in Borg subscription | Included in Borg subscription |
Not published by the vendor: release, context, modalities, open weights, vendor api list price / 1m tokens.
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.
| Metric | Borg Fusion | Borg Fusion Coding |
|---|---|---|
| Time to first token (gateway proxy) p50 | Not published | Not published |
| Tokens per second (end to end) p50 | Not published | Not published |
| 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.
Borg Fusion: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 0 requests. Minimum 100 samples per published request metric.
Borg Fusion Coding: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 0 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
Borg Fusion is listed for multi-step tasks, whereas Borg Fusion Coding is listed for multi-step coding work. Choosing between Borg Fusion and Borg Fusion Coding requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Borg Fusion | Borg Fusion Coding |
|---|---|---|
| Context window | Not published | Not published |
| Reasoning modes | Not published / low, medium, high | Not published / low, medium, high, max |
| Release date | Not published | Not published |
| API price input / 1M | Not published | Not published |
| API price output / 1M | Not published | Not published |
| Time to first token (gateway proxy) | Not published | Not published |
| Output tokens per second (whole turn) | Not published | Not published |
| Request success | Not published | Not published |
| Coding bench | Not published | Not published |
FAQ
How do Borg Fusion and Borg Fusion Coding compare for coding?
Borg Fusion has a Borg coding benchmark of not published; Borg Fusion Coding has not published. The Borg Fusion–Borg Fusion Coding coding comparison cannot establish an overall winner from this small test alone.
How quickly do Borg Fusion and Borg Fusion Coding start responding on Borg?
Borg median first response for Borg Fusion is not published; for Borg Fusion Coding it is not published. The Borg Fusion–Borg Fusion Coding gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Borg Fusion and Borg Fusion Coding?
The listed API rate for Borg Fusion is not published; for Borg Fusion Coding it is not published. Neither Borg Fusion nor Borg Fusion Coding has its Borg subscription charge represented by those provider API rates.
Claude
GPT