Pricing
Pay for tokens. Nothing else.
No subscriptions, no minimums, no per-seat anything. Prices are per million tokens, prompt and completion combined.
| Class | Interactive | Batch (0.7×) | What lives here |
|---|---|---|---|
| Nano · ≤3B | $0.04 | $0.028 | classification, extraction, routing |
| Small · 7–9B | $0.1 | $0.07 | the volume workhorse |
| Mid · 13–34B | $0.3 | $0.21 | premium consumer hardware |
| Large · 70B | $0.7 | $0.49 | scarce supply, priced accordingly |
| Embeddings | $0.01 | $0.007 | bulk vectorization |
The multipliers, in the open
Latency class
Batch 0.7× · interactive 1.0×. Batch jobs queue for idle capacity — that's why they're cheaper, not a gimmick.
Privacy tier
Open is the listed price; verified and private carry premiums for scarcer, accountable capacity.
Surge
Up to 1.5× when demand outruns supply — visible on the response, never silent. Operators earn more in surge, which recruits supply.
Where the money goes: operators keep the majority of revenue (≥50% at steady state); the rest funds verification hardware and margin. The split is part of the product, not a secret.