# System1 Models

> Low-cost hosted decision models for routing, classification and scoring. One Jev-compatible API, with Global and EU tiers.

Sign in with Google at https://system1models.ai/login, create an API key in your dashboard and start with 100M input tokens free. Prepaid credit top-ups use Stripe with invoices. Top-ups: Germany today; EU businesses and more countries soon.

## Models and launch pricing
s1-fast (Plumb-4B, text): Global $0.025 / EU $0.034 per 1M input tokens; output tokens free.
s1-pro (Winnow-12B Q8, text): Global $0.034 / EU $0.040 per 1M input tokens; output tokens free.
Image input: coming soon. USD rates exclude applicable taxes. EUR rates are published at https://system1models.ai/pricing.

## Tiers and data
Today both tiers run in Finland: API gateway on Hetzner in Helsinki, GPU inference on Verda in Finland. Global has lower priority on shared EU capacity. Client-to-API TLS 1.3; gateway-to-GPU WireGuard encryption. Prompts and outputs are never stored or used for training.
The decentralized Global network is rolling out; it carries no customer traffic today. We will announce before Global traffic moves to the network. EU inference stays on contracted EU operators and never uses that network.

## API and MCP
API base: https://api.system1models.ai
POST /v1/systemone: model, state, and exactly one typed question (noul, choice or score).
GET /v1/models (alias /models): live model registry.
Authenticate inference with Authorization: Bearer <API key>; choose S1-Region: global|eu.
Hosted MCP: https://api.system1models.ai/mcp (streamable HTTP, JSON-RPC; Bearer API key). Tools: decide, list_models, get_usage, get_balance.
Swagger UI: https://system1models.ai/docs/api/reference
OpenAPI snapshot: https://system1models.ai/openapi.json
Authoritative API OpenAPI: https://api.system1models.ai/openapi.json

## Resources
- [llms.txt](https://system1models.ai/llms.txt)
- [llms-full.txt](https://system1models.ai/llms-full.txt)
- [Sign in and create a key](https://system1models.ai/login?next=/dashboard)
- [Quickstart](https://system1models.ai/docs/quickstart)
- [API reference (Swagger UI)](https://system1models.ai/docs/api/reference)
- [OpenAPI JSON](https://system1models.ai/openapi.json)
- [Hosted MCP setup](https://system1models.ai/mcp)
- [Models](https://system1models.ai/models)
- [Launch pricing](https://system1models.ai/pricing)
- [EU tier](https://system1models.ai/eu)
- [Agent guide](https://system1models.ai/agents)
- [DPA](https://system1models.ai/legal/dpa)
- [Sub-processors](https://system1models.ai/legal/subprocessors)
- [Security](https://system1models.ai/security)

## HTTP operations
- GET /v1/models: List Models V1
- GET /models: List Models Legacy Compat
- GET /v1/auth/{provider}: Begin Oauth Sign In
- GET /v1/auth/{provider}/callback: Complete Oauth Sign In
- POST /v1/auth/magic-link: Request Magic Link
- POST /v1/auth/magic-link/consume: Consume Magic Link
- GET /v1/session: Get Dashboard Session
- GET /v1/session/csrf: Get Session Csrf Token
- POST /v1/session/logout: Logout Session
- GET /v1/legal/status: Legal Status
- POST /v1/legal/accept: Accept Legal
- GET /v1/dpa/status: Dpa Status
- POST /v1/dpa/accept: Accept Dpa
- GET /v1/api-keys: List Api Keys
- POST /v1/api-keys: Create Api Key
- DELETE /v1/api-keys/{key_id}: Revoke Api Key
- GET /v1/account/retention: Get Account Retention
- PUT /v1/account/retention: Update Account Retention
- GET /v1/balance: Get Account Balance
- GET /v1/usage: Get Account Usage
- POST /v1/systemone: Systemone
- POST /v1/multimodal: Multimodal
- POST /v1/billing/checkout: Create Billing Checkout
- GET /v1/billing/invoices: List Billing Invoices
- GET /v1/billing/invoices/{checkout_id}: Get Billing Invoice
- GET /v1/billing/invoices/{checkout_id}/document: Get Billing Invoice Document
- POST /v1/billing/refunds: Create Billing Refund

Dashboard operations use the signed-in session; changes require X-CSRF-Token. The hosted MCP get_usage and get_balance tools use your API key for account-scoped access. Google sign-in is the available sign-in method.

## Request example
curl https://api.system1models.ai/v1/systemone \
  -H "Authorization: Bearer $SYSTEM1_API_KEY" \
  -H "Content-Type: application/json" \
  -H "S1-Region: global" \
  -d '{"model":"s1-fast","state":"Mia owns a red bicycle.","questions":{"color":{"type":"choice","instructions":"Which color is the bicycle?","criteria":{"red":null,"blue":null}}}}'

Exactly one question per inference request. State is at most 16 KiB serialized JSON; the full body is at most 6 MiB and model input is at most 4,096 tokens. Consult the OpenAPI schemas for exact bounds and error responses.

## Region selection
Choose per API key or per request with S1-Region: global|eu. EU inference remains in Finland. The Global network is in development: independent GPU operators, encrypted traffic, Ed25519 signatures on requests and responses, and operator registration and performance scoring secured by blockchain technology. Today Global runs on the same EU GPU capacity as EU, at lower priority.

## EUR launch rates
s1-fast: Global €0.022, EU €0.030 per 1M input tokens.
s1-pro: Global €0.030, EU €0.035 per 1M input tokens.
Output tokens are free. Rates exclude applicable taxes.

## Browser discovery
WebMCP tools use public site data: get_pricing, list_models, estimate_cost, switch_region, open_page, get_quickstart, get_api_endpoints. Cost estimates exclude taxes, trial credits and output-token charges. Tools never handle keys, sign in, top up credits or call inference.

## Legal and benchmarks
The legal routes are published on this site. Accept the Terms and DPA during signup; consult the sub-processor list for Google sign-in and Stripe payments. They never receive your prompts. Benchmark results cover several sources at https://system1models.ai/benchmarks; JevBench is run by our founder and is disclosed as one input among several. System1 Models is an independent service and is not affiliated with TypeSafe or OpenAI.