{"data":{"id":"deepinfra/Qwen/Qwen3.5-9B","provider_id":"deepinfra","name":"Qwen/Qwen3.5-9B","modalities":["text","image"],"context_window":262144,"family":"Qwen3.5-9B","status":"active","description":"Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.","architecture":null,"supported_parameters":["chat","vlm","vision","reasoning_effort","reasoning"],"created_at":null,"canonical_slug":"Qwen/Qwen3.5-9B","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":60404,"model_id":"deepinfra/Qwen/Qwen3.5-9B","unit":"token","input_per_1m_usd":0.1,"output_per_1m_usd":0.15,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/Qwen/Qwen3.5-9B","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}]}}