Perplexity's contextual embedding model Embed V2 Context (9B/0.6B) is live on OpenRouter
antoine_chaffin · x · 2026-11-21
Perplexity's Embed V2 Context multimodal embedding models are now available on OpenRouter in 9B and 0.6B sizes, covering text, images, and document pages.
Key feature: send a document as an ordered list of chunks and each chunk's embedding reflects the whole document — aimed at RAG and search pipelines. Returns 2048-dim vectors by default (1024 optional); both sizes share an embedding space so indexes built with one can be queried with the other. Priced at $0.12/M tokens with 32K context, and separate inputtype modes for queries vs documents.
More from Models
- InferenceBench ranks agents on LLM serving speedup: Claude Opus 5.5 tops at 12.08x, agents lose to simple hyperparameter search — maksym_andr · 2026-11-21
- Cloudflare launches multimodal model clairic-flash, trending on Hugging Face — Cloudflare · 2026-11-21
- Inkling 2 Mini used to clone Apple Spotlight search 8 hours after release — IgorCarron · 2026-11-21
- 6 free open models to replace paid Claude for every job: chat, coding, OCR, speech — alex_verem · 2026-11-21
- Inkling 2 Mini edges Qwen 3.8 27B on coding (277 vs 272) but struggles on PC hardware — Ubunta · 2026-11-21
- Inkling 2 Mini on PC: edges out Qwen 3.8 27B on coding tests but painful to run — Ubunta · 2026-11-21