DeepSeek-V4-Flash API enters public beta with upgraded agent capabilities

Skip to main content # Change Log ## Date: 2026-07-31​ ### DeepSeek-V4-Flash Update​ The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged — simply set the model name to `deepseek-v4-flash` to use the latest version. Significantly enhanced agent capabilities, with benchmark results far exceeding V4-Pro-Preview: Terminal Bench 2.1: 82.7 NL2Repo: 54.2 Cybergym: 76.7 DeepSWE: 54.4 Toolathlon verified: 70.3 Agent Last Exam: 25.2 Automation Bench (Public): 25.1 DSBench-FullStack: 68.7 DSBench-Hard: 59.6 [...] ## Date: 2026-04-24​ ### DeepSeek-V4​ The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base\_url remains unchanged, and the model parameter should be set to `deepseek-v4-pro` or `deepseek-v4-flash`. The two legacy API model names, `deepseek-chat` and `deepseek-reasoner`, will be discontinued in

Image 4: Avatar of antirez antirez•Jul 31 RT @deepseek_ai: 🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark… DeepSeek has launched the DeepSeek-V4-Flash Official API in public beta, featuring significantly upgraded agent capabilities with improved benchmark performance. Image 5: Avatar of rohanpaul_ai Rohan Paul•Jul 31 DeepSeek-V4-Flash is now live as a public beta API, s 82.7 on Terminal Bench 2.1 and beating the larger Pro-Preview. the reason to route expensive work to the bigger sibling is gone, and long agent loops are where spend piles up. [...] DeepSeek-V4-Flash has launched as a public beta API, scoring 82.7 on Terminal Bench 2.1 and outperforming the larger Pro-Preview model. This positions the smaller, cheaper Flash model as a viable replacement for expensive long agent loops previously routed to the bigger sibling. Image 6: Avatar of iscienceluvr Tanishq, Ph.D. at ICML•Jul 31 "We’ve massive

## Techmeme's Post ### Techmeme 1d · DeepSeek rolls out the official V4 Flash API in public beta, touting enhanced agent capabilities and benchmark scores "far surpassing" V4 Pro Preview Full context: DeepSeek Unveils Public Beta API for Flagship AI Model bloomberg.com DeepSeek Unveils Public Beta API for Flagship AI Model

We have a new model today coming from Deepseek. Yes, Deepseek version 4 Flash is officially live now and in public beta. They massively upgraded its agent capabilities and the benchmark scores might be surprising for a lot of us. So, [music] what exactly is new? Let's get into it. So, if we look at the Deepseek version for Flash, you're going to notice one thing. This [music] model is not trying to compete with Opus 5 or GPT 5.6 Soul. rather this model is trying to compete with itself. Number one is showing that they made a model which is much more efficient, faster and costs way less than their pro version which is a good release for them. But not only that, this model is quite competitive when it comes to GLM 5.2, Opus 4.8. So keep that in mind when we look at the benchmarks. You're not [...] the same model architecture as the preview version and the official release of Deepseek version 4 Pro not the preview is coming soon. So there's one more model coming from the Deepseek team. So

Log inSign up ## Post user avatar DeepSeek @deepseek\_ai 🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇 🔷 The official V4-Flash now natively supports the Responses API format and is fully adapted for Codex! Check out the configuration details in our official API docs: api-docs.deepseek.com/quick\_start/ag… 6:56 AM · Jul 31, 20268.1MViews user avatar DeepSeek @deepseek\_ai Jul 31 [...] DeepSeek @deepseek\_ai Jul 31 ⚠️ Note 🔷 DeepSeek-V4-Flash-0731 keeps the exact same model architecture and size as the preview version. 🔷 Today's upgrade applies ONLY to the DeepSeek-V4-Flash API. The DeepSeek-V4-Pro API and App/Web models remain unchanged for now. The official release of DeepSeek-V4-Pro 429K user avatar Unsloth AI @UnslothAI Jul 31 If DeepSeek-V4-Flash is this

Log inSign up ## Post user avatar DeepSeek @deepseek\_ai Jul 31 🚀 DeepSeek-V4-Flash Official API is now LIVE in public beta! 🔷 We’ve massively upgraded its Agent capabilities—benchmark scores are now far surpassing the V4-Pro-Preview. Check out the massive performance leap below! 👇 🔷 The official V4-Flash now natively supports the 7.8M user avatar DeepSeek @deepseek\_ai ⚠️ Note 🔷 DeepSeek-V4-Flash-0731 keeps the exact same model architecture and size as the preview version. 🔷 Today's upgrade applies ONLY to the DeepSeek-V4-Flash API. The DeepSeek-V4-Pro API and App/Web models remain unchanged for now. The official release of DeepSeek-V4-Pro is coming ASAP! Stay tuned. 6:56 AM · Jul 31, 2026407.4KViews user avatar John Shina @JohnShina91 Jul 31