{"data":{"id":"deepinfra/Qwen/Qwen3-Embedding-4B","provider_id":"deepinfra","name":"Qwen/Qwen3-Embedding-4B","modalities":["text"],"context_window":32768,"family":"Qwen3-Embedding-4B","status":"active","description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).","architecture":null,"supported_parameters":["embed"],"created_at":null,"canonical_slug":"Qwen/Qwen3-Embedding-4B","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"alibaba","creator_name":"Alibaba","cheapest_provider":null,"cheapest_provider_name":null,"cheapest_price":null,"savings_pct":null,"savings_basis":null,"provider":{"id":"deepinfra","name":"DeepInfra","website":"https://deepinfra.com","categories":["text","image","audio","video"],"docs_url":"https://deepinfra.com/pricing","notes":"Secondary live feed from DeepInfra's public models API. Prices are DeepInfra's rates, not the origin lab's. Does not block the OpenRouter sync.","role":"host"},"prices":[{"id":60373,"model_id":"deepinfra/Qwen/Qwen3-Embedding-4B","unit":"token","input_per_1m_usd":0.02,"output_per_1m_usd":null,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/Qwen/Qwen3-Embedding-4B","notes":"DeepInfra public models API. Token and character rates are already USD per 1M. Per-image and per-second rates are stored as flat USD. Discount, when present, is not applied.","last_verified_at":"2026-10-08T17:11:32.756Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":null,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}