ModelPriceWatch.com
Last scan 2026-09-20 Models tracked 265 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Jev 1.13

by TypeSafe AI

Current budget cheap tier
Email me when Jev 1.13 gets cheaper
Availability: Sold only by TypeSafe, on a single endpoint (POST /v1/systemone). The versioned id is jev-1.13.0; the aliases jev-latest and jev-preview both resolve to it today. No reseller carries it — it is absent from the OpenRouter catalogue (446 rows, read 2026-09-20). Published rate limits are 250,000 tokens per second and 1,200 requests per minute, and the page warns they "can change without notice" while TypeSafe scales. The rate card prints no release date, and the GET /v1/models call that returns one needs an API key, so no release date is published here.

Today's price · per 1M tokens

Input

$0.042

per 1M tokens

Output

$0

per 1M tokens

Blended

$0.032

blended $/1M — 3:1 weighted input:output

How this price is scoped: First-party list price. TypeSafe makes Jev and sells it only on its own API, so docs.typesafe.ai/models is the rate card. That page prints ONE figure for Jev 1.13 — "Price (per Btok / per Mtok) $42 / $0.042" — and the two are the same INPUT rate in two units, not an input/output pair: a Btok is a billion tokens and an Mtok is a million. The note under the table reads "Charged per input token. Output tokens are free." We publish the per-Mtok form. The $0.00 output is therefore the maker's own printed rate on its own rate card — not a host promotion, not an introductory offer, and not an unknown coerced to zero. Second source, independent of the capture and agreeing exactly: LiteLLM's typesafe/jev-1.13.0 entry records input_cost_per_token 4.2e-08 and output_cost_per_token 0.0, cited to this same page.

Source: official TypeSafe AI pricing · read MODELPRICEWATCH.COM · 2026-09-20

Price receipt

No confirmed receipt. We hold dated captures of TypeSafe AI's pricing page, but none of them tied Jev 1.13 to the price above on that page, so we do not claim this number is sourced. Check the provider's page directly before relying on it.

Overview

TypeSafe AI's flagship, and the first of what it calls System One models: you send a block of state plus typed questions — yes/no, choice or score — and get structured answers with calibrated probabilities back, instead of generated text. The billing follows that shape. TypeSafe charges for input tokens only, at $0.042 per 1M tokens ($42 per 1B, the unit its own rate card leads with), and the same card states that output tokens are free — so the $0 output on this row is a rate the maker published, not a number we are missing. Text in only; images, audio and video have to be turned into text or structured fields first. One request carries a 64,000-token budget covering the state and every question together, with a tighter 32,000-token limit on the state plus the single longest question.

Capabilities

struck through = not supported
Input 1/4
Text ✓ Image Audio Video
Output
Text ✓
Features 0/9
Prompt caching Reasoning Coding Fast inference Long context Open weights Multimodal Web search Realtime

Specifications

Provider
TypeSafe AI
Context window
64K tokens
Modality
text
Parameters
Proprietary
Open source
No — proprietary
Released
—
Status
Current
Last updated
Tags
budget

Availability verified: — listed on TypeSafe AI's own page

Official pricing page