{"data":{"id":"deepinfra/sesame/csm-1b","provider_id":"deepinfra","name":"sesame/csm-1b","modalities":["audio"],"context_window":null,"family":"csm-1b","status":"active","description":"CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.","architecture":null,"supported_parameters":["tts"],"created_at":null,"canonical_slug":"sesame/csm-1b","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"sesame","creator_name":"Sesame","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":60277,"model_id":"deepinfra/sesame/csm-1b","unit":"character","input_per_1m_usd":7,"output_per_1m_usd":null,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/sesame/csm-1b","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_characters is USD per 1M characters.","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}]}}