{"data":{"id":"deepinfra/ibm-granite/granite-4.2-8b","provider_id":"deepinfra","name":"ibm-granite/granite-4.2-8b","modalities":["text"],"context_window":131072,"family":"granite-4.2-8b","status":"active","description":"Granite-4.2-8B is the mid-size reasoning model in the Granite 4.2 family. It delivers strong performance on reasoning-intensive tasks by leveraging built-in <think>...</think> chain-of-thought. It supports flexible thinking modes — full thinking (default), non-thinking, and low-effort — allowing users to balance depth vs. latency on a per-query basis.","architecture":null,"supported_parameters":["chat","prompt_cache","reasoning"],"created_at":null,"canonical_slug":"ibm-granite/granite-4.2-8b","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"ibm-granite","creator_name":"IBM","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":60351,"model_id":"deepinfra/ibm-granite/granite-4.2-8b","unit":"token","input_per_1m_usd":0.06,"output_per_1m_usd":0.25,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/ibm-granite/granite-4.2-8b","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 0.015/1M.","last_verified_at":"2026-10-08T18:23:40.278Z","source":"deepinfra","confidence":"official","cache_read_per_1m_usd":0.015,"cache_write_per_1m_usd":null,"cache_write_1h_per_1m_usd":null,"pricing_detail":null,"long_context_override":false}]}}