{"data":{"id":"deepinfra/openai/whisper-large-v3-turbo","provider_id":"deepinfra","name":"openai/whisper-large-v3-turbo","modalities":["audio"],"context_window":null,"family":"whisper-large-v3-turbo","status":"active","description":"Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper \"Robust Speech Recognition via Large-Scale Weak Supervision\" by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting. Whisper large-v3-turbo is a finetuned version of a pruned Whisper large-v3. In other words, it's the exact same model, except that the number of decoding layers have reduced from 32 to 4. As a result, the model is way faster, at the expense of a minor quality degradation.","architecture":null,"supported_parameters":["stt"],"created_at":null,"canonical_slug":"openai/whisper-large-v3-turbo","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"openai","creator_name":"Openai","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":60397,"model_id":"deepinfra/openai/whisper-large-v3-turbo","unit":"second_audio","input_per_1m_usd":null,"output_per_1m_usd":null,"flat_usd":0.00000333,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/openai/whisper-large-v3-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. input_seconds is USD per second of input audio.","last_verified_at":"2026-10-08T18:23:40.278Z","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}]}}