{"data":{"id":"deepinfra/Qwen/Qwen2.5-72B-Instruct","provider_id":"deepinfra","name":"Qwen/Qwen2.5-72B-Instruct","modalities":["text"],"context_window":32768,"family":"Qwen2.5-72B-Instruct","status":"active","description":"Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilingual capabilities for over 29 languages.","architecture":null,"supported_parameters":["chat"],"created_at":null,"canonical_slug":"Qwen/Qwen2.5-72B-Instruct","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"alibaba","creator_name":"Alibaba","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.37,"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":60360,"model_id":"deepinfra/Qwen/Qwen2.5-72B-Instruct","unit":"token","input_per_1m_usd":0.36,"output_per_1m_usd":0.4,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct","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}]}}