Image-understanding model Jev 1.14 lands on Runware at $0.042 per 1M input tokens
aziz4ai · x · 2026-10-31
TypeSafeAI's Jev 1.14 image-understanding model is now live on Runware. It can read images and answer typed questions about them, with a new Box question type that returns an object's location as four 0–1 edge fractions plus confidence.
Key points:
- Images can appear anywhere text goes: state, instructions, or criteria
- PNG/JPEG, 280–1568px per side; experimental mode via the TypeSafe-Danger-Zone-Images: true header
- Switch model ID to typesafe:[email protected]
- Pricing: from $0.042 per 1M input tokens including images, output free
More from Multimodal
- AI-generated Doritos USB drive concept mocks design-product photography — Delahuntagram · 2026-10-31
- Krea 2 + H3 morph workflow auto-generates soundtracks via SigLIP2 and Suno MCP — Accurate_Public4674 · 2026-10-31
- Suno ships MCP Beta, dev uses it to sync motion graphics to AI-generated music — enggirlfriend · 2026-10-31
- Mischief launches video model trained from lab-grown brain cells at 0.5¢ per second — evilsocket · 2026-10-31
- A full structured prompt for a 30-second hyper-real horror video sequence — LudovicCreator · 2026-10-31
- Creepy AI horror short made with Seedance 2.5: the abandoned hospital hallway — LudovicCreator · 2026-10-31