{"data":{"id":"deepinfra/thenlper/gte-base","provider_id":"deepinfra","name":"thenlper/gte-base","modalities":["text"],"context_window":512,"family":"gte-base","status":"active","description":"The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large, GTE-base, and GTE-small. The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval, semantic textual similarity, text reranking, etc.","architecture":null,"supported_parameters":["embed"],"created_at":null,"canonical_slug":"thenlper/gte-base","catalog_source":"deepinfra","host_id":"deepinfra","host_name":"DeepInfra","creator_id":"thenlper","creator_name":"Thenlper","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":60369,"model_id":"deepinfra/thenlper/gte-base","unit":"token","input_per_1m_usd":0.005,"output_per_1m_usd":null,"flat_usd":null,"currency":"USD","effective_at":"2026-10-08","source_url":"https://deepinfra.com/thenlper/gte-base","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}]}}