deepseek-ai/DeepSeek-V4-Flash-0731
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731">deepseek-ai/DeepSeek-V4-Flash-0731
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 well above its weight.
Artificial Analysis https://artificialanalysis.ai/models/deepseek-v4-flash">rank it 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 https://artificialanalysis.ai/models/deepseek-v4-flash#intelligence-comparison-tabs">Intelligence Index vs.
Cost per Intelligence Index Task chart:
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" />
I got https://gist.github.com/simonw/83bfb1171792f1e7a4d8935b5e82317e#prompt">a disappointing pelican from it using the default reasoning level via OpenRouter:
https://static.simonwillison.net/static/2026/deepseek-flash-v4-default.png" />
But when I bumped reasoning level up to high I got https://gist.github.com/simonw/83bfb1171792f1e7a4d8935b5e82317e#options">something much better:
llm -m openrouter/deepseek/deepseek-v4-flash-0731 -t pelican -o reasoning_effort high
https://static.simonwillison.net/static/2026/deepseek-flash-v4-high.png" />
Via https://news.ycombinator.com/item?id=49120299">Hacker News
Tags: https://simonwillison.net/tags/ai">ai, https://simonwillison.net/tags/generative-ai">generative-ai, https://simonwillison.net/tags/llms">llms, https://simonwillison.net/tags/pelican-riding-a-bicycle">pelican-riding-a-bicycle, https://simonwillison.net/tags/deepseek">deepseek, https://simonwillison.net/tags/llm-release">llm-release, https://simonwillison.net/tags/openrouter">openrouter, https://simonwillison.net/tags/ai-in-china">ai-in-china, https://simonwillison.net/tags/artificial-analysis">artificial-analysis