{"id":"deepseek-ai/deepseek-v4-flash","aliases":["deepseek/deepseek-v4-flash","deepseek/deepseek-v4-flash-20260423","hf:deepseek-ai/deepseek-v4-flash","openrouter:deepseek/deepseek-v4-flash"],"displayName":"DeepSeek-V4-Flash","author":"deepseek-ai","createdAt":"2026-04-22T06:04:20.000Z","updatedAt":"2026-09-08T15:44:27.512Z","popularityRank":16,"metadata":{"modalities":["text","text-generation"],"inputModalities":["text"],"outputModalities":["text"],"contextLength":1048576,"maxOutputTokens":384000,"family":"deepseek-flash","modelsDev":{"provider":"openrouter","sourceUrl":"https://models.dev/api.json","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","lastUpdated":"2026-04-24","releaseDate":"2026-04-24","capabilities":{"reasoning":true,"tool_call":true,"attachment":false,"temperature":true,"open_weights":true,"structured_output":true},"knowledgeCutoff":"2025-05"},"tokenizer":"DeepSeek","license":"mit","licenseStatus":"approved","weightsAvailable":true,"hostedInferenceAllowed":true,"gated":false,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_completion_tokens","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_a","top_k","top_logprobs","top_p"],"providerNames":[],"designArenaCategories":["3d","asciiart","codecategories","dataviz","gamedev","svg","uicomponent","website"],"isModerated":false},"availability":"unknown","externalBest":null,"multivibeNetwork":null,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","runtimes":[],"protocols":[],"harnesses":[]}