{"slug": "deepseek-puts-v4-flash-api-into-public-beta", "title": "DeepSeek puts V4-Flash API into public beta", "summary": "DeepSeek has launched the public beta of its V4-Flash API, featuring upgrades for agent tasks, scoring 82.7 on Terminal Bench 2.1 and 54.4 on DeepSWE. The update adds Responses API support and Codex adaptation, while the V4-Pro API and app/website models remain unchanged.", "body_md": "DeepSeek has put the formal version of its V4-Flash API into public beta, with an upgrade focused on agent tasks. The company says the model scored 82.7 on Terminal Bench 2.1 and 54.4 on DeepSWE, among other benchmarks.\n\nThe release adds support for the Responses API and is adapted for Codex. DeepSeek says the V4-Flash-0731 model keeps the same structure and size as the preview version but has been retrained. The update applies only to the V4-Flash API; the V4-Pro API and the models used on DeepSeek’s app and website have not changed. [[DeepSeek API Docs](https://api-docs.deepseek.com/zh-cn/updates/)]", "url": "https://wpnews.pro/news/deepseek-puts-v4-flash-api-into-public-beta", "canonical_source": "https://technode.com/2026/07/31/deepseek-puts-v4-flash-api-into-public-beta/", "published_at": "2026-07-31 07:19:25+00:00", "updated_at": "2026-07-31 07:41:02.344117+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products", "ai-agents"], "entities": ["DeepSeek", "V4-Flash API", "V4-Flash-0731", "V4-Pro API", "Terminal Bench 2.1", "DeepSWE", "Responses API", "Codex"], "alternates": {"html": "https://wpnews.pro/news/deepseek-puts-v4-flash-api-into-public-beta", "markdown": "https://wpnews.pro/news/deepseek-puts-v4-flash-api-into-public-beta.md", "text": "https://wpnews.pro/news/deepseek-puts-v4-flash-api-into-public-beta.txt", "jsonld": "https://wpnews.pro/news/deepseek-puts-v4-flash-api-into-public-beta.jsonld"}}