Compare · Last verified 2026-10-15

OpenAI Decisions vs Jev: pricing, limits, and which to use

Verdict

As of 2026-10-15, Jev (TypeSafe AI) costs $0.042 per 1M input tokens versus $0.10 for the OpenAI Decisions API, publishes its context limits (64k/request, 262k long-context), and offers pinnable version IDs (jev-1.14.0, jev-1.13.0). OpenAI Decisions is still public beta with a single alias model (gpt-6-luna), but accepts images and offers ZDR, HIPAA, and US/EU data residency for eligible customers.

Pick OpenAI Decisions for: Teams already on OpenAI that need image input, enterprise data controls (ZDR/HIPAA), or EU residency.
Pick Jev for: Cost-sensitive, text-only workloads that want a pinned model version and published context limits.

Side-by-side

	OpenAI Decisions API	Jev (TypeSafe AI)
Vendor	OpenAI	TypeSafe AI
Category	Decision model	Decision model
Price	$0.10 per 1M input tokens; no output, cache-read, or cache-write charges. [Verified 2026-10-15 against official page] Regional processing premiums and long-context input multipliers apply (amounts not stated on the guide). [Verified 2026-10-15 against official page]	$0.042 per 1M input tokens ($42 per billion) for both Jev 1.14 and 1.13; output tokens free. Long-context mode costs the same per token. [Verified 2026-10-15 on docs.typesafe.ai/models]
Limits	Context window and rate limits are not stated on the Decisions guide. [Unverified — not published on the page checked]	64k tokens per request / 32k per question by default; 262k for both with the opt-in long-context header (slower and less accurate per TypeSafe). [Verified 2026-10-15 on docs.typesafe.ai/models]
Status	Public beta; OpenAI says it expects GA "in the coming weeks". [Verified 2026-10-15 against official page] Data controls: ZDR and HIPAA for eligible customers; data residency/regional processing in the US and Europe (EEA + Switzerland). [Verified 2026-10-15 against official page] No published SLA, dated model snapshot, or deprecation schedule found for /v1/decisions. [Absence noted 2026-10-14/15; not confirmed against enterprise terms]	Jev 1.14 available from October 14, 2026 per TypeSafe docs. [Verified 2026-10-15 on docs.typesafe.ai/models] Correction: an earlier version of this page showed $0.42/1M taken from jevtypesafeai.com, a domain we could not tie to TypeSafe. TypeSafe’s own docs show $0.042. [Correction logged 2026-10-15]
Fit notes	Good fit: classification, routing, prioritization, and review queues with app-owned thresholds set from your own labeled examples. Only the alias gpt-6-luna is documented — behavior can change under you. Run a canary eval and log the model string on every call. No rationale is returned; if users need an explanation, pair it with a generative model and human review. OpenAI Usage Policies restrict automating high-stakes decisions in sensitive areas (e.g. critical infrastructure, product safety components, medical) without human review. Keep it advisory; never the sole authority.	Pin a versioned ID (e.g. jev-1.13.0) rather than an alias so thresholds don’t drift with version changes. Text-oriented; check image support for your version in TypeSafe docs before relying on it.

FAQ

Is Jev cheaper than the OpenAI Decisions API?

Yes. As of 2026-10-15, Jev lists $0.042 per 1M input tokens and the OpenAI Decisions API lists $0.10 per 1M input tokens; neither charges for output tokens.

Can I pin a model version?

Jev publishes versioned IDs (jev-1.14.0, jev-1.13.0). OpenAI documents only the gpt-6-luna alias for /v1/decisions, so behavior can change without a new model ID.

Do both accept images?

The OpenAI Decisions API accepts base64 images. Jev is text-oriented; Vercel AI Gateway returns 400 for image requests to typesafe-ai/jev.

Methodology

Every fact in the table is copied from the vendor's official page (or OpenRouter where noted) and labeled with the date it was last verified. Items we could not confirm are marked unverified. Prices are list prices per 1M input tokens before regional or volume adjustments. See our methodology.