Find the lane.Choose how you pay.
Pay for the lane that ran, or choose a plan for the decisions in front of it. A model you attach is billed by its publisher. The table lists Separator lane rates.
| Lane | Work | Meter | Input / output |
|---|---|---|---|
| reason-1 | Explanations and judgment | 1M tokens | $1.50 / $6.00 |
| code-1 | Patches and reviews | 1M tokens | $1.25 / $5.00 |
| write-1 | Drafts and captions | 1M tokens | $1.00 / $4.00 |
| search-1 | Lookups with sources | 1M tokens | $0.80 / $3.00 |
| ops-1 | Checklists and follow-ups | 1M tokens | $1.10 / $4.40 |
| vision-1 | Stills from a prompt | image | $0.02 per image |
| vision-1 | Short moving images | second | $0.04 per second |
| speech-1 | Transcripts and spoken replies | minute | $0.06 per minute |
Showing 8 of 8 lanes. These are Separator lane rates, not a publisher token price.
Questions
What is a decision?+
A decision is one call to Separator. It includes the type, the contract, the model or the fan-out list, and the milliseconds spent choosing. Tokens generated by the model on a lane are metered separately.
Do I pick the model myself?+
You can. Send model “separator” and Separator chooses from your allow-list. Send a lane id such as code-1 and the hop stays on that lane if the type fits the contract. A mismatch is refused.
When does a request split?+
When it contains more than one type of work. Closing the books, writing the summary, and reading a clause are three parts. Each part is a small request to a different model. The response lists them.
Is the millisecond figure a benchmark we publish from production?+
No. The product is designed so the routing decision — not the model’s full answer — lands in milliseconds, under 10 ms as the target. The consoles on this site illustrate that contract. They are not a live measurement of the API.
Is the API generally available?+
It is in preview. Request a key and VeloxitySI will integrate Separator with the stack you run. The status page marks the API as preview on purpose.
Separator
Put a typed route in front of the models you already call.
Decision
explanation
reason-1
4.2 ms