{"data":{"id":"deepinfra/zai-org/GLM-5.3-Flash","provider_id":"deepinfra","name":"zai-org/GLM-5.3-Flash","modalities":["text","image"],"context_window":1048576,"family":"GLM-5.3-Flash","status":"active","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","architecture":null,"supported_parameters":["chat","vlm","vision","prompt_cache","reasoning"],"created_at":null,"canonical_slug":"zai-org/GLM-5.3-Flash","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"z-ai","creator_name":"Z.ai","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":60342,"model_id":"deepinfra/zai-org/GLM-5.3-Flash","unit":"token","input_per_1m_usd":0.15,"output_per_1m_usd":0.5,"flat_usd":null,"currency":"USD","effective_at":"2026-10-21","source_url":"https://deepinfra.com/zai-org/GLM-5.3-Flash","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. Cache read 0.03/1M.","last_verified_at":"2026-10-21T00:15:40.358Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":0.03,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}