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.
The 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]