DeepInfra offers NVIDIA Nemotron-3.5-Embed-8B-BF16 as a multimodal embedding API at USD 0.035 per 1M input tokens; image input USD 0.070 per 1M image tokens. The published context window is 32,768 tokens; billing is for processed input tokens, not generated text output.
Use-case fit and limitations from the existing resource record.
Available
Non-price resource facts only; pricing, history, and evidence stay in their own sections.
Decision visuals remain traceable to the existing source and verification record.
Independent ranking · native prices · evidence-linked · commercial relationships isolated from scoring and publication.