deepseek-ai/DeepSeek-V4-Flash-0731

<p><strong><a href="https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731">deepseek-ai/DeepSeek-V4-Flash-0731</a></strong></p> The latest release in DeepSeek's V4 family, "with substantially enhanced agentic capabilities". It's 304 billion parameters - 167GB on Hugging Face - but it appears to punch <em>well</em> above its weight.</p> <p>Artificial Analysis <a href="https://artificialanalysis.ai/models/deepseek-v4-flash">rank it</a> ahead of MiniMax M3 - a 428B model. It's $0.14/million input and $0.27/million output pricing means this may currently be the best value-per-intelligence model out there. It's looking very good on the <a href="https://artificialanalysis.ai/models/deepseek-v4-flash#intelligence-comparison-tabs">Intelligence Index vs. Cost per Intelligence Index Task</a> chart:</p> <p><img alt="Scatter plot from Artificial Analysis titled with axes &quot;Artificial Analysis Intelligence Index&quot; (20 to 65) and &quot;Cost per Task (USD, Log Scale)&quot; ($0.02 to $3), with a green &quot;Most attractive quadrant&quot; box in the upper left and a dotted &quot;Pareto line&quot;. DeepSeek V4 Flash 0731 (max) is highlighted in dark blue at roughly $0.028 and an intelligence score of 50, sitting alone at the far left edge of the green quadrant where the Pareto line jumps sharply upward. Models of similar or lower intelligence like MiniMax-M3, Kimi K3 (low), GLM-5.1 and Kimi K2.6 cost ten times more, and the models that beat it (Grok 4.5, Gemini 3.6 Flash, GLM-5.2, Kimi K3, Claude Opus 5, Claude Fable 5, GPT-5.6 Sol) all sit far to the right at $0.4 to $3 per task." src="https://static.simonwillison.net/static/2026/deepseek-flash-chart.webp" /></p> <p>I got <a href="https://gist.github.com/simonw/83bfb1171792f1e7a4d8935b5e82317e#prompt">a disappointing pelican</a> from it using the default reasoning level via OpenRouter:</p> <p><img alt="Flat vector illustration of a white pelican with a long neck and large orange beak pouch, hovering above a mangled blue a