{"data":{"id":"deepseek/deepseek-v4-flash-0731:batch","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","architecture":{"tokenizer":"DeepSeek","instruct_type":null,"modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[]}}