Drex 1.5 vs Jev

Drex 1.5

The hosted endpoint has a public OpenAPI document, published limits and pinned model versions, at $0.05 per million input tokens with no output charge. The #1 under 10B claim rests on Nace's own run, since Drex is absent from both public boards. Weights carry Open RAIL-M, which requires a commercial licence above $1 million in revenue or funding.

Jev

Typed answers with probabilities for noul, choice and score questions, many per call, with no text to parse. Early access behind a waitlist, with no free tier or free credits found.

Drex 1.5

1. Call https://console.nace.ai/v1/systemone with Authorization: Bearer nace_sk_..., and pin model drex-v1.5 rather than drex-latest in production.
2. Stop on 402 insufficient_credit or 402 payment_required until credit is topped up or the unpaid invoice is paid.
3. Retry 429 and 529 after retry-after-ms. On a 422 for an unknown model, use one of the ids the error message lists.
4. Keep state below 131,072 tokens and the body below 1,048,576 bytes, and send at most 512 questions per request.
5. Keep the key on a server. A key in browser code is exposed, and the /v1 routes send no Access-Control-Allow-Origin header.
6. Check usage.input_tokens and the usage CSV after retries, since /v1/systemone documents no idempotency key.

Jev

1. Put every independent question about one state into a single call. They run in parallel and the state is billed once
2. Pin jev-1.13.0 instead of jev-latest once you've tuned confidence thresholds
3. Back off exponentially on 429 and 529. The limits move with demand
4. Keep state to what the decision needs. Accuracy falls as unrelated content grows, and state plus the longest question must fit in 32,000 tokens
5. Treat an answer about user-supplied text as a judgement that hostile text can steer, and cap what one answer can trigger