To celebrate the launch of GPT-4o, we’ve upgraded the Playground! You can now test GPT-4o’s vision capabilities and compare output across models. platform.openai.com/playground

Tidy up your dashboard by archiving projects and API keys you’re no longer using. You can also set project spend limits—perfect for managing costs across projects or experiments without worrying about going over budget. help.openai.com/en/articles/91…

We’ve improved the navigation on platform.openai.com. Switch easily between orgs and projects, and access the docs in one click.

You can now customize how your files are chunked and change the number of chunks returned in the Assistants API’s File Search tool. platform.openai.com/docs/assistant…

If you need models to only call one function, you can now disable parallel function calling by setting `parallel_tool_calls: false`. platform.openai.com/docs/guides/fu…

Did you know you can fine-tune models for function calling? Well, you can! As of today, we have added support for the `tools` parameter in the Fine-tuning API, which means you can now also fine-tune for parallel function calling. platform.openai.com/docs/guides/fi…

The playground now supports function calling! Quickly define and test functions within the dashboard. platform.openai.com/playground/cha…

We're making building with the text-to-speech API even easier by adding it to the Playground! Just enter a message to generate audio in one of six preset voices. platform.openai.com/playground/tts

Customize GPT-4o mini for your application with fine-tuning. Available today to tier 4 and 5 users, we plan to gradually expand access to all tiers. First 2M training tokens a day are free, through Sept 23. platform.openai.com/docs/guides/fi…

We’re launching our new Admin API—you can now manage invites, users, projects, and service accounts programmatically. Our new Audit Logs API also helps you keep track of logins and changes to your organization. platform.openai.com/docs/api-refer…

We’re taking OpenAI DevDay on the road! Join us this fall in San Francisco, London, or Singapore for hands-on sessions, demos, and best practices. Meet our engineers and see how developers around the world are building with OpenAI. openai.com/devday/

Introducing Structured Outputs in the API—model outputs now adhere to developer-supplied JSON Schemas. openai.com/index/introduc…

Our newest GPT-4o model is 50% cheaper for input tokens and 33% cheaper for output tokens. It also supports Structured Outputs, which ensures model outputs exactly match your JSON Schemas.

We’re expanding GPT-4o mini fine-tuning access today to all developers on usage tiers 1-5. You’ll get 2M training tokens a day for free through Sept 23. platform.openai.com/docs/guides/fi…

This model is also now available in the API as `chatgpt-4o-latest`. We recommend `gpt-4o-2024-08-06` for most API usage, but are excited to give developers access to test our latest improvements for chat use cases. platform.openai.com/docs/models/gp…

We're launching fine-tuning for GPT-4o so you can improve performance and accuracy for your apps. openai.com/index/gpt-4o-f…

Reminder to all developers: we're offering 1M free training tokens per day for GPT-4o fine-tuning until Sept 23, and 2M free training tokens for GPT-4o mini! openai.com/index/gpt-4o-f…

We just rolled out enhanced controls for File Search in the Assistants API to help improve the relevance of your assistant's responses. You can now inspect the search results returned by the tool and configure their rankings. platform.openai.com/docs/assistant…