TypeSafe Jev on LiteLLM

TypeSafe AI's Jev launches on LiteLLM today in v1.103.0-rc. Jev is a decision model: it returns a choice, a score, or a yes/no probability instead of text, so it has its own evaluate endpoint rather than /chat/completions. LiteLLM proxies that endpoint with logging and cost tracking.

Pricing

$0.042 per 1M input tokens, no output charge. Spend is logged under the versioned model TypeSafe reports (typesafe/jev-1.13.0 today), even when you request jev-latest.

Usage

Set your TypeSafe key once on the proxy, then replace https://api.typesafe.ai with LITELLM_PROXY_BASE_URL/typesafe. Clients only need a LiteLLM virtual key.

export TYPESAFE_API_KEY="your-typesafe-api-key"

curl -X POST "http://0.0.0.0:4000/typesafe/v1/systemone" \
  -H "Authorization: Bearer $LITELLM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "state": "Help! My payouts have been failing for 3 days.",
    "model": "jev-latest",
    "questions": {
      "department": {
        "type": "choice",
        "instructions": "Which team should handle this?",
        "criteria": {
          "billing": "Payments, invoicing, refunds",
          "technical": "Bugs, outages, integrations"
        }
      }
    }
  }'

The response is TypeSafe's own, unchanged. Any path under /typesafe/ is forwarded, so GET /typesafe/v1/models lists the available models. Full details in the TypeSafe pass-through docs.

Feedback

Running Jev through LiteLLM and hitting something unexpected? Open a GitHub discussion.