TEXT · PLUMB-4B
s1-fast
Global $0.025 · EU $0.034 per 1M input tokens; output free. Local model-server p95 from the launch load test: 244 ms. View measurement details →
See pricing →Models · text
Model profiles and public evidence
The hosted decision-model profiles are s1-fast (Plumb-4B) and s1-pro (Winnow-12B Q8), both for text. Each profile card links to its local model-server p95 measurement. Public results from multiple sources provide separate context for model quality; they credit the model authors and do not measure the hosted System1 service. Read the sources and limits →
TEXT · WINNOW-12B Q8
s1-pro
Global $0.034 · EU $0.040 per 1M input tokens; output free. Local model-server p95 from the same test: 644 ms. View measurement details →
See pricing →NEW ACCOUNTS
Start free
Sign in with Google, create an API key and use both models right away. Your first 100M input tokens are free.
Get API key →Two tiers
Choose the tier that fits your data.
Same models, same API, same request shape. Choose per API key or per request with one header.
GLOBALMost affordable
Global — built to scale worldwide
The most affordable way to run decision models at scale. Global is moving onto a decentralized compute network: independent GPU operators worldwide, encrypted network traffic, every request and response cryptographically signed, and operator registration and performance scoring secured by blockchain technology.
Today
While the network rolls out, Global runs on the same EU GPU capacity as the EU tier — encrypted in transit, at lower priority than EU traffic. We will announce before any Global traffic moves to the network.
- s1-fast $0.025 · s1-pro $0.034 per 1M input tokens
- Output tokens free
- Best for high volume and non-sensitive data
EU
Highest data protection
Highest data protectionEU — for the strictest data-protection requirements
For teams with the highest data-protection demands or strict EU regulatory requirements. EU requests run only on contracted operators inside the EU, and inference data never leaves the EU.
- s1-fast $0.034 · s1-pro $0.040 per 1M input tokens
- Inference data stays in the EU (Finland)
- Contracted EU operators only — never the decentralized network
- Data Processing Agreement at signup, published sub-processor list
- Prompts and outputs are never stored or used for training
- Built for GDPR
Sign-in (Google) and payments (Stripe) are handled by the sub-processors listed on our sub-processor page; they never receive your prompts.
Public benchmark context
Model evidence from multiple sources
Each benchmark has equal visual weight. Read its metric and coverage separately; different tasks, adapters and hardware can produce different trade-offs.
| Model profile | Decision Index0.2.1Chance-corrected index / 100Independent community | Workflow Evalsdatasets 2026-09-28 · code 0ac3b8aModel-reference agreementTypeSafe · reference vendor | Jev Rerank Bench2026-09-25Dataset-macro nDCG@10 / 1Independent author | JevBench1.5.1Composite score / 100Same founder as System1 | ImageJevBench0.1.4Composite score / 100Same founder as System1 |
|---|---|---|---|---|---|
| s1-fastPlumb-4B | Not measured¹ | Not measured¹ | Not measured¹ | 71.56 | Not measured¹ |
| s1-proWinnow-12B Q8 | 50.02 | Not measured¹ | 0.634 | 73.23 | 43.56 |
| TypeSafe referenceJev 1.13.0 | 57.91 | 67.8 | 0.670 | 72.13 | Not measured¹ |
¹ Not measured means no comparable published measurement was verified for this model; it is not a zero. Results concern the tested model implementations, not the System1 service. ImageJevBench uses a separate image path; image input for customers is coming soon.
Conflict of interest: JevBench and ImageJevBench are run by the founder of System1 Models. Workflow Evals is published by TypeSafe AI, the vendor of the reference model. It measures model-reference agreement, not human-labelled accuracy. No overall score is published while comparable coverage is incomplete. Method and sources →
Image decisions
Image input is coming soon
The image evaluation is one equal column in the matrix above. Its result belongs to a separate Winnow Q8 image implementation. Image input for System1 customers is coming soon; today the API accepts text.
Jev is a trademark of TypeSafe AI; references to Jev are nominative compatibility references only. System1 Models is not affiliated with TypeSafe AI and does not resell Jev.