{"data":{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","provider_id":"deepinfra","name":"meta-llama/Llama-3.3-70B-Instruct-Turbo","modalities":["text"],"context_window":131072,"family":"Llama-3.3-70B-Instruct-Turbo","status":"active","description":"Llama 3.3-70B Turbo is a highly optimized version of the Llama 3.3-70B model, utilizing FP8 quantization to deliver significantly faster inference speeds with a minor trade-off in accuracy. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on various benchmarks, including conversational tasks, language translation, and text generation.","architecture":null,"supported_parameters":["chat"],"created_at":null,"canonical_slug":"meta-llama/Llama-3.3-70B-Instruct-Turbo","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"meta","creator_name":"Meta","cheapest_provider":"deepinfra","cheapest_provider_name":"DeepInfra","cheapest_price":0.155,"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":60315,"model_id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","unit":"token","input_per_1m_usd":0.1,"output_per_1m_usd":0.32,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/meta-llama/Llama-3.3-70B-Instruct-Turbo","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}]}}