Poe

We made a major upgrade to Poe App Creator, and it is now built on top of Claude Code. This update will generally produce significantly better results, especially when building and iterating on complex applications inside of Poe. As usual, Poe apps you create with App Creator can build on top of any combination of the 200+ models on Poe. You can try the new experience at https://lnkd.in/gYHKffJB, and across the Poe iOS, Android, Mac, and Windows apps.

New: Poe Leaderboard We launched a leaderboard that shows the most used AI models and apps across Poe's platform and API. Rankings are updated daily based on total token usage across the 200+ text, image, video, and audio bots on Poe. To view the current rankings, go to https://lnkd.in/g34wkU-r (currently desktop and web only).

Now available: Claude Haiku 4.5! Anthropic’s newest model balances intelligence and speed while delivering high performance in coding and agentic tasks. Claude Haiku 4.5 is available at https://lnkd.in/gJjQxpnv, available across all platforms, and accessible through the Poe API.

Veo 3.1 and Veo 3.1 Fast are now on Poe. The new release brings improvements to dialogue, sound effects, and overall video quality, which includes native 1080p resolution. Veo 3.1 Fast is optimized for quicker generation times and lower cost. You can try Veo 3.1 at https://poe.com/Veo-3.1 and Veo 3.1 Fast at https://lnkd.in/gvSgiPH5 across all of our apps and in the Poe API.

Today we're adding transparent pricing to Poe. This means you can easily view USD costs for all models and compare our rates with other platforms. Models from Anthropic, Google, and OpenAI currently cost 10-30% less on Poe, with no hidden fees. To view a model's input/output token price, simply go to the model's page. We also recently added receipts in the app and API to make it easier to view and understand your actual usage, so that you can better manage and control spending. Anyone with a Poe subscription (including API users) can now purchase additional credits whenever needed. Subscriptions start at $4.99/month, and you can manage everything at poe.com/api_key. We hope this makes it straightforward to compare our offering directly to standard rates as you decide what platform best suits your needs. This is especially important for API users and people who benefit from high-usage and multi-model access in a single subscription. Today we're also expanding what you can do with the Poe API. Tool calling support is now available for all OpenAI, Anthropic, and Google models. This means you can use the Poe API to power agentic workflows directly with code or in applications like Kilo Code, Roo Code, Cline, Codex CLI, n8n and more. We have more planned for the weeks and months ahead including new API tools, features, and integrations. You can get started with Poe today at https://poe.com. We can't wait to see what you create!

New on Poe: Sora 2 and Sora 2 Pro! OpenAI’s new flagship video model generates hyper-realistic clips with synced audio and physical accuracy, allowing you to effortlessly turn text prompts into cinematic creations. Sora 2 Pro produces longer, more complex scenes at higher resolution than base Sora 2. Sora 2 Pro is available at https://poe.com/Sora-2-Pro, while Sora 2 is at https://poe.com/sora-2. You can try both across all platforms, and can be used through the Poe API. Enjoy!

New: GPT-Image-1-Mini! A faster and more cost-efficient version of OpenAI’s popular image gen model, it accepts both text and image inputs while creating high quality images with impressive instruction following, text rendering, and realism. GPT-Image-1-Mini is available at https://lnkd.in/gpDxjm25, across all platforms, and via the Poe API.

Now on Poe: GPT-5 Pro! GPT-5 Pro is OpenAI’s most intelligent model ever. It’s great for assisting on complex tasks where you need high accuracy and depth of reasoning. You can try GPT-5 Pro at https://poe.com/GPT-5-Pro, across all platforms, and through the Poe API.

Try the Amazon Nova family of bots today on Poe!

New: DeepSeek-V3.2-Exp! DeepSeek AI's new experimental model delivers strong performance for long-context queries. You can try it at https://lnkd.in/gjEjyBdh, in the Poe app across platforms, and use it in the Poe API.