aiqbench takeAI Products

TypeSafe AI has updated its Jev model to support multimodal inputs via images and bounding boxes while expanding context windows to 262k tokens. This release demonstrates a practical evolution in handling complex, high-volume data streams within a type-safe framework, offering developers new capabilities for vision-language tasks at a competitive cost.

Sources coveringMarkTechPost, InfoQ

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

TypeSafe AI Releases Jev 1.14 With Images, Box Type and 262k Context

MarkTechPostOctober 15, 20261 min read

TypeSafe AI released Jev 1.14 under the jev-preview alias. The System One model adds experimental image input, a Box bounding-box type and an opt-in 262k-token context, at $0.042 per million input tokens. The post TypeSafe AI Releases Jev 1.14 With Images, Box Type and 262k Context appeared first on MarkTechPost.

Read the full article at MarkTechPost

Read at MarkTechPost ↗Ask about this article