Updated
Desk
Access
Public listings for calling Jev, as of the stories on this desk. Price, context window, and quota are whatever that host published. We did not send a request to any of these endpoints. Community servers that copy the same HTTP shape sit on repos. Jevflake is a dbt package that calls TypeSafe's API from Snowflake SQL. duckdb-jev does the same from DuckDB. prompt_jev() is MotherDuck's hosted SQL function on paid plans. jsort calls the same API, or OpenRouter, once per pair. For how a listing gets on the digest, see method.
TypeSafe API
POST /v1/systemone with a TypeSafe key. Docs list jev-1.13.0 at $0.042 per million input tokens, free output, 1,200 requests per minute, 64k for the whole request and 32k for state plus the longest question. TypeSafe posted on September 20 that there is no waitlist. New accounts start with $5 of credit, about 120 million tokens. On September 21 it posted API and console issues at 08:30 UTC and We are back at 09:53 UTC. The status incident Console is unavailable is marked resolved at 08:16 UTC. On September 22, at 06:19 UTC, TypeSafe posted that new signups are paused. Existing signups continue. The post does not say when signups reopen.
Vercel AI Gateway
typesafe-ai/jev on the Gateway, with an experimental evaluate method in the AI SDK. Listed September 16. The model card lists input and output as Free until promotional pricing ends September 25, 2026. Vercel reported nearly 13% of paid Gateway teams calling it in the first 24 hours. The form router template calls typesafe-ai/jev through experimental_evaluate and keeps the destination at confidence 0.95, with gpt-5.6-luna-fast on the rest. A Vercel deploy uses an OIDC token. Gateway quotas are not the same as a TypeSafe console key.
Cloudflare Workers AI
Rita Kozlov posted that Jev was live on Cloudflare AI Gateway. Workers AI serves typesafe/jev via env.AI.run. The model card lists a 32,000-token window. Cloudflare files it under text generation. Dashboard rates are not the $0.042 figure.
Netlify AI Gateway
A September 17 changelog: install @typesafe-ai/sdk, construct TypeSafeClient inside Functions, bill against Netlify credits. Sample routes a contact form between sales, support, and spam.
OpenRouter
Beta listing for ~typesafe/jev-latest at TypeSafe's public price. The call is POST /api/alpha/decisions, not chat completions. OpenRouter labeled the endpoint alpha and the model beta.
Venice
Beta Decisions API on September 18: POST /api/v1/decisions, model jev-latest, same $0.042 rate, 64k / 32k split. Same Venice key as chat and image. Venice says it keeps no copy of the state. The handler is also at /systemone for a TypeSafe SDK base-URL swap. API only; no web-app surface.
MotherDuck
prompt_jev() on paid MotherDuck plans. A SQL statement sends a text column and a choice, score, or yes/no question. The published AG News script reads result.choice and result.confidence. The 100,000-row table is vendor-reported: 89% accuracy, 2,484 rows/s, $0.50, 40 seconds.
LiteLLM
Self-hosted proxy in v1.103.0-rc. TYPESAFE_API_KEY lives on the proxy; clients send a LiteLLM virtual key to POST /typesafe/v1/systemone. Spend is logged as typesafe/jev-1.13.0 even when the request asks for jev-latest. A typesafe guardrail can drop older tool results below a 0.2 relevance score before the generator runs.