B.AI has announced that its Responses API now supports DeepSeek model series. Developers can use their B.AI API Key to directly call DeepSeek models within the Codex client, integrating DeepSeek's reasoning and code generation capabilities into daily workflows. The setup requires only configuring the API Key and Base URL, allowing seamless switching between DeepSeek and GPT models for tasks such as code generation, comprehension, debugging, refactoring, and collaboration. Previously, B.AI supported GPT models via Codex; this expansion adds a powerful alternative. B.AI will continue to broaden its model portfolio and API compatibility to deliver a more open and efficient programming assistant experience for global developers.
On September 2, B.AI said its Responses API now works with the DeepSeek model series. Developers can use a B.AI API Key to call DeepSeek models directly inside the Codex client, bringing DeepSeek's reasoning and code generation into everyday development work.
Setup is simple. After configuring the API Key and Base URL, developers can switch between DeepSeek and GPT models as needed for code generation, understanding, debugging, refactoring, and development collaboration. B.AI had already supported GPT models through Codex, and adding DeepSeek gives users more model options inside the Codex environment.
B.AI also said it plans to keep expanding its model matrix and API compatibility, with the goal of offering developers worldwide a more open and efficient programming assistant experience.
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
