deepseek-v4-flash-0731 · DeepSeek
DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.
DeepSeek-V4-Flash-0731(deepseek-v4-flash-0731) is an open-source MoE large language model developed by the Chinese AI company DeepSeek, with support for a million-token context window. It is designed for coding, complex reasoning, tool use, agentic workflows, and long-document processing. Its advantages include strong performance with fewer active parameters and improved efficiency through DSpark speculative decoding. Compared with DeepSeek V4-Flash Preview, it offers significantly stronger coding and agent capabilities, while outperforming DeepSeek V4-Pro Preview on several benchmarks with fewer active parameters.
DeepSeek V4 Flash 0731 has a 1,000,000 token context window.
On AIHubMix, DeepSeek V4 Flash 0731 costs $0.142 per million input tokens and $0.284 per million output tokens. Cached input reads are billed at $0.028 per million tokens.
DeepSeek V4 Flash 0731 accepts text input.
DeepSeek V4 Flash 0731 supports tool calling, function calling, structured outputs and thinking. Per-protocol parameter support is listed in the capability table on this page.
DeepSeek V4 Flash 0731 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to deepseek-v4-flash-0731 — no other code changes needed.
DeepSeek V4 Flash 0731 is developed by DeepSeek. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
DeepSeek V4 Flash 0731 was released on July 31, 2026 by DeepSeek.
DeepSeek’s officially released new multimodal visual-understanding model…
DeepSeek V4 Pro 0813 is DeepSeek’s high-performance general-purpose reasoning and agent…
DeepSeek V4 Flash 0731 Fast is a high-speed deployment of DeepSeek’s agentic model…
(This model currently points to the older 0423 version; if you need to request the latest…
(This model currently points to the older 0423 version; if you need to request the latest…
DeepSeek-V3.2 is an efficient large language model equipped with DeepSeek Sparse…
Use DeepSeek V4 Flash 0731 via the AIHubMix unified API — one interface for every major LLM.