Article
CommunityJev Integrations & Adapters
Jev in Pydantic AI Gateway
Pydantic's AI Gateway forwards Jev natively as a bring-your-own-key TypeSafe provider, so one gateway key covers spend views, limits, and input guardrails while TypeSafeModel turns each output field into a question.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Author
- Marcelo Trylesinski (Pydantic)
- Last verified
- Oct 2026
Highlights
- Add TypeSafe AI under Logfire's Gateway providers; Test & continue fetches models with your key, so a bad key fails at setup.
- Curl posts to https://gateway-us.pydantic.dev/proxy/typesafe/v1/systemone with the gateway key, model jev-latest, and a noul question.
- The TypeSafe Python SDK works by pointing base_url at https://gateway-us.pydantic.dev/proxy/typesafe.
- Requests are metered into the same spend view and limits as language models, and input guardrails run on state, instructions, and criteria.
- Pydantic AI's TypeSafeModel maps each field of the output type to a question; the Ticket example returns urgent=True and area='billing'.
Watch out
A vendor article: TypeSafe is a bring-your-own-key provider, so the gateway adds metering, guardrails, and one key but does not change Jev's cost or speed. Streaming is refused before forwarding and Jev is absent from the chat playground; the $0.042 per million input tokens figure is quoted from earlier reporting.
Questions about this entry
Short answers drawn from the linked project or page.
In Logfire, open Gateway, then Providers, and add a provider; pick TypeSafe AI, paste your TypeSafe API key, and click Test & continue. The dialog then defaults to jev-latest and gives a snippet with your gateway key filled in.
It forwards TypeSafe's System One API natively, so POST to https://gateway-us.pydantic.dev/proxy/typesafe/v1/systemone with model jev-latest, a state, and a map of typed questions, using your Pydantic gateway key.
Yes. Add the SDK with uv add typesafe-sdk, then pass your gateway key and base_url https://gateway-us.pydantic.dev/proxy/typesafe to TypeSafeClient with model jev-latest, and the request routes through the gateway.
Every request is metered and appears in the same spend view and limits as your language models; input guardrails run on the state, the instructions, and the criteria before the request goes upstream; and your application holds one gateway key.
No. Streaming requests are refused before they are forwarded because System One answers in one response, and Jev is not in the chat playground, since there is nothing to chat with.
Install the typesafe extra for pydantic-ai-slim, build a TypeSafeModel with a TypeSafeProvider that carries the gateway key and base URL, and set output_type to a Pydantic model; each field becomes a question, such as urgent and area for a ticket.
Marcelo Trylesinski wrote it on 25 September 2026. The post says the gateway does not change what Jev costs or how fast it answers, and that TypeSafe is a bring-your-own-key provider rather than a gateway-managed one.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev 1.14 is now on OpenRouter
X: Jev lands on the Vercel AI Gateway
X: Jev as an LLM guardrail inside Agentgateway
YouTube: Greg Isenberg and Ryan Vogel on the businesses Jev unlocks, and a path in through the Vercel AI Gateway.
More Jev resources like this
Concentrate's beta /v1/decisions endpoint serves TypeSafe's Jev with the same request and response shapes as TypeSafe's System One API and OpenRouter, returning calibrated probabilities for noul, choice, and score questions.
Jev Integrations & AdaptersDocs#community#gateway#api
Community
LiteLLM's proxy adds TypeSafe guardrail hooks and a Jev complexity classifier for policy judgments and request routing across 100+ model providers.
Jev Integrations & Adapters#community#python#gateway
Community
BerriAI/litellmPython
BerriAI/litellmPythonLiteLLM serves decision models on two routes that share one provider list: /v1/decisions for OpenAI-format bodies and /v1/systemone for System One bodies, with Jev available as the typesafe/jev-latest provider.
Jev Integrations & AdaptersDocs#community#litellm#gateway
Community
MLflow's AI Gateway lists TypeSafe Jev among its evaluation providers: a typesafe passthrough at /gateway/typesafe/v1/systemone forwards raw System One requests using the server-side TypeSafe key, separate from MLflow judges.
Jev Integrations & AdaptersDocs#community#mlflow#gateway
Community
Fly.io's TypeSafeAI connector gives Sprites access to Jev without the API key entering the machine: the Sprites gateway attaches the organization's encrypted key, and each Sprite sets only TYPESAFE_BASE_URL plus a placeholder key.
Jev Integrations & AdaptersArticle#community#fly-io#agents
Community
Opper's model page for Jev 1.13: one route through the Opper gateway at $0.04 per million input tokens, text-only input with a 64K window, RLCD-trained calibrated probabilities, and a Pac-Man benchmark run across 100 games.
Jev Integrations & Adapters#community#gateway#benchmarks
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.