Poe
@poe.com
The best AI, all in one place. ChatGPT, Claude 4, R1, Gemini, FLUX, Veo 3, ElevenLabs and more. At poe.com, or for iOS, Android, Mac, or Windows at poe.com/download.
DeepSeek‑V3.2 is live on Poe!
This next-generation foundation model is designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/DeepSeek-V3.....
This next-generation foundation model is designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/DeepSeek-V3.....
December 2, 2025 at 9:12 PM
DeepSeek‑V3.2 is live on Poe!
This next-generation foundation model is designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/DeepSeek-V3.....
This next-generation foundation model is designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance.
You can try it in the Poe app on all platforms and in the Poe API at poe.com/DeepSeek-V3.....
Flux.2 is live on Poe!
Black Forest Labs’ new state-of-the-art image model delivers sharp detail with strong style control and text rendering.
Powered by fal on Poe, try it for concept art, product shots, and high-fidelity edits. (1/2)
Black Forest Labs’ new state-of-the-art image model delivers sharp detail with strong style control and text rendering.
Powered by fal on Poe, try it for concept art, product shots, and high-fidelity edits. (1/2)
November 25, 2025 at 6:13 PM
Flux.2 is live on Poe!
Black Forest Labs’ new state-of-the-art image model delivers sharp detail with strong style control and text rendering.
Powered by fal on Poe, try it for concept art, product shots, and high-fidelity edits. (1/2)
Black Forest Labs’ new state-of-the-art image model delivers sharp detail with strong style control and text rendering.
Powered by fal on Poe, try it for concept art, product shots, and high-fidelity edits. (1/2)
Claude Opus 4.5 just landed on Poe!
It leads on 7 out of 8 programming languages on SWE-bench Multilingual and jumps 10.6% over Claude Sonnet 4.5 on Aider Polyglot.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Claude-Opus-....
It leads on 7 out of 8 programming languages on SWE-bench Multilingual and jumps 10.6% over Claude Sonnet 4.5 on Aider Polyglot.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Claude-Opus-....
November 24, 2025 at 7:45 PM
Claude Opus 4.5 just landed on Poe!
It leads on 7 out of 8 programming languages on SWE-bench Multilingual and jumps 10.6% over Claude Sonnet 4.5 on Aider Polyglot.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Claude-Opus-....
It leads on 7 out of 8 programming languages on SWE-bench Multilingual and jumps 10.6% over Claude Sonnet 4.5 on Aider Polyglot.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Claude-Opus-....
You can remix other script bots to build off of others’ creations. This video shows how PixelGIFGenerator can be remixed into a bot that is based on a consistent character. (4/9)
November 24, 2025 at 7:43 PM
You can remix other script bots to build off of others’ creations. This video shows how PixelGIFGenerator can be remixed into a bot that is based on a consistent character. (4/9)
Introducing script bots, a new way to combine models and automate workflows on Poe.
Script bots are created through vibe coding with Script Bot Creator and can combine any of the 200+ text, image, video, and audio models on Poe, plus any other bot on the platform. (1/9)
Script bots are created through vibe coding with Script Bot Creator and can combine any of the 200+ text, image, video, and audio models on Poe, plus any other bot on the platform. (1/9)
November 24, 2025 at 7:43 PM
Introducing script bots, a new way to combine models and automate workflows on Poe.
Script bots are created through vibe coding with Script Bot Creator and can combine any of the 200+ text, image, video, and audio models on Poe, plus any other bot on the platform. (1/9)
Script bots are created through vibe coding with Script Bot Creator and can combine any of the 200+ text, image, video, and audio models on Poe, plus any other bot on the platform. (1/9)
New! Nano Banana Pro is on Poe!
Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages. (1/2)
Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages. (1/2)
November 20, 2025 at 5:54 PM
New! Nano Banana Pro is on Poe!
Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages. (1/2)
Nano Banana Pro (Gemini 3 Pro Image Preview) can make detailed, context-rich visuals, precisely edit or restyle input images with exceptional fidelity, and even generate legible text in images in multiple languages. (1/2)
Now on Poe: Grok 4.1 Fast
This includes two models: Reasoning is best for agentic tool‑calling and non‑reasoning is a faster option for less complex tasks. Both support 2 million tokens of context. (1/2)
This includes two models: Reasoning is best for agentic tool‑calling and non‑reasoning is a faster option for less complex tasks. Both support 2 million tokens of context. (1/2)
November 20, 2025 at 1:19 AM
Now on Poe: Grok 4.1 Fast
This includes two models: Reasoning is best for agentic tool‑calling and non‑reasoning is a faster option for less complex tasks. Both support 2 million tokens of context. (1/2)
This includes two models: Reasoning is best for agentic tool‑calling and non‑reasoning is a faster option for less complex tasks. Both support 2 million tokens of context. (1/2)
Gemini 3 Pro is now on Poe!
Benchmark results indicate it will offer state-of-the-art performance on math, coding, computer use, and long‑horizon agent tasks.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-3.0-Pro.
Benchmark results indicate it will offer state-of-the-art performance on math, coding, computer use, and long‑horizon agent tasks.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-3.0-Pro.
November 18, 2025 at 4:29 PM
Gemini 3 Pro is now on Poe!
Benchmark results indicate it will offer state-of-the-art performance on math, coding, computer use, and long‑horizon agent tasks.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-3.0-Pro.
Benchmark results indicate it will offer state-of-the-art performance on math, coding, computer use, and long‑horizon agent tasks.
You can try it in the Poe app on all platforms and in the Poe API at: poe.com/Gemini-3.0-Pro.
It’s easy to get started: create a new group chat from the home screen and invite friends. Like all chats on Poe, history syncs in real time across devices, so you can start on desktop and continue on mobile, and anyone invited can use any Poe client to join the group. (6/8)
November 17, 2025 at 5:58 PM
It’s easy to get started: create a new group chat from the home screen and invite friends. Like all chats on Poe, history syncs in real time across devices, so you can start on desktop and continue on mobile, and anyone invited can use any Poe client to join the group. (6/8)
Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation.
Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)
Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)
November 17, 2025 at 5:58 PM
Introducing group chat on Poe: a new way to collaborate with any AI and anyone you know, all in a single conversation.
Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)
Now available to all users worldwide, groups can interact with any of the 200+ text, image, video, or audio models on Poe, plus any creator-made bots. (1/8)
Four new OpenAI models are now on Poe: GPT-5.1-Instant, GPT-5.1, GPT-5.1-Codex, and GPT-5.1-Codex-Mini.
Instant is smart and more conversational, the full 5.1 model includes dynamic reasoning, and Codex models power coding via the Poe API. (1/2)
Instant is smart and more conversational, the full 5.1 model includes dynamic reasoning, and Codex models power coding via the Poe API. (1/2)
November 13, 2025 at 7:36 PM
Four new OpenAI models are now on Poe: GPT-5.1-Instant, GPT-5.1, GPT-5.1-Codex, and GPT-5.1-Codex-Mini.
Instant is smart and more conversational, the full 5.1 model includes dynamic reasoning, and Codex models power coding via the Poe API. (1/2)
Instant is smart and more conversational, the full 5.1 model includes dynamic reasoning, and Codex models power coding via the Poe API. (1/2)
MiniMax-M2 is now available on Poe!
This open source model has a 200k token context window, has 230b parameters with an MoE architecture, and excels at coding and agent workflows.
This open source model has a 200k token context window, has 230b parameters with an MoE architecture, and excels at coding and agent workflows.
November 4, 2025 at 6:42 PM
MiniMax-M2 is now available on Poe!
This open source model has a 200k token context window, has 230b parameters with an MoE architecture, and excels at coding and agent workflows.
This open source model has a 200k token context window, has 230b parameters with an MoE architecture, and excels at coding and agent workflows.
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. (1/2)
October 17, 2025 at 3:57 PM
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. (1/2)
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. (1/2)
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. (1/2)
October 16, 2025 at 6:35 PM
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. (1/2)
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. (1/2)
Now available: Claude Haiku 4.5!
Anthropic’s newest model balances intelligence and speed while delivering high performance in coding and agentic tasks. (1/2)
Anthropic’s newest model balances intelligence and speed while delivering high performance in coding and agentic tasks. (1/2)
October 15, 2025 at 10:01 PM
Now available: Claude Haiku 4.5!
Anthropic’s newest model balances intelligence and speed while delivering high performance in coding and agentic tasks. (1/2)
Anthropic’s newest model balances intelligence and speed while delivering high performance in coding and agentic tasks. (1/2)
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. (1/2)
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. (1/2)
October 15, 2025 at 6:16 PM
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. (1/2)
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. (1/2)
The Poe API now supports tool calling 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 KiloCode, RooCode, Cline, N8N, Codex CLI and more.
October 13, 2025 at 6:19 PM
The Poe API now supports tool calling 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 KiloCode, RooCode, Cline, N8N, Codex CLI and more.
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. (1/5)
October 10, 2025 at 4:24 PM
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. (1/5)
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. (1/2)
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. (1/2)
October 7, 2025 at 4:37 PM
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. (1/2)
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. (1/2)
New: DeepSeek-V3.2-Exp!
DeepSeek's new experimental model delivers strong performance for long-context queries.
You can try it at poe.com/DeepSeek-V3...., in the Poe app across platforms, and use it in the Poe API.
DeepSeek's new experimental model delivers strong performance for long-context queries.
You can try it at poe.com/DeepSeek-V3...., in the Poe app across platforms, and use it in the Poe API.
September 30, 2025 at 2:10 AM
New: DeepSeek-V3.2-Exp!
DeepSeek's new experimental model delivers strong performance for long-context queries.
You can try it at poe.com/DeepSeek-V3...., in the Poe app across platforms, and use it in the Poe API.
DeepSeek's new experimental model delivers strong performance for long-context queries.
You can try it at poe.com/DeepSeek-V3...., in the Poe app across platforms, and use it in the Poe API.
Now on Poe: Claude Sonnet 4.5
Anthropic’s most advanced model yet is one of the best in the world for complex tasks and excels in real-world coding. (1/2)
Anthropic’s most advanced model yet is one of the best in the world for complex tasks and excels in real-world coding. (1/2)
September 29, 2025 at 5:59 PM
Now on Poe: Claude Sonnet 4.5
Anthropic’s most advanced model yet is one of the best in the world for complex tasks and excels in real-world coding. (1/2)
Anthropic’s most advanced model yet is one of the best in the world for complex tasks and excels in real-world coding. (1/2)
New: You can now branch conversations from any message on Poe. Each branch copies the conversation up to that point into a new chat so you can test prompts, actions, or ideas and steer the direction without starting over. (1/2)
September 26, 2025 at 5:10 PM
New: You can now branch conversations from any message on Poe. Each branch copies the conversation up to that point into a new chat so you can test prompts, actions, or ideas and steer the direction without starting over. (1/2)
In audio, ElevenLabs defends its TTS lead (~74% share), with its new v3 model seeing swift adoption.
Music models also emerged on Poe this summer, with ElevenLabs Music taking an early 10.1% share of the audio category, ahead of Google's Lyria at 3.3%. (5/6)
Music models also emerged on Poe this summer, with ElevenLabs Music taking an early 10.1% share of the audio category, ahead of Google's Lyria at 3.3%. (5/6)
September 25, 2025 at 5:09 PM
In audio, ElevenLabs defends its TTS lead (~74% share), with its new v3 model seeing swift adoption.
Music models also emerged on Poe this summer, with ElevenLabs Music taking an early 10.1% share of the audio category, ahead of Google's Lyria at 3.3%. (5/6)
Music models also emerged on Poe this summer, with ElevenLabs Music taking an early 10.1% share of the audio category, ahead of Google's Lyria at 3.3%. (5/6)
OpenAI extends its lead in text with GPT-5, but Google is gaining ground.
OpenAI models now command over 50% of text usage. At the same time, Google’s Gemini-2.5 series has steadily grown to ~10% share, reversing its earlier decline and showing sustained momentum against the market leaders. (4/6)
OpenAI models now command over 50% of text usage. At the same time, Google’s Gemini-2.5 series has steadily grown to ~10% share, reversing its earlier decline and showing sustained momentum against the market leaders. (4/6)
September 25, 2025 at 5:09 PM
OpenAI extends its lead in text with GPT-5, but Google is gaining ground.
OpenAI models now command over 50% of text usage. At the same time, Google’s Gemini-2.5 series has steadily grown to ~10% share, reversing its earlier decline and showing sustained momentum against the market leaders. (4/6)
OpenAI models now command over 50% of text usage. At the same time, Google’s Gemini-2.5 series has steadily grown to ~10% share, reversing its earlier decline and showing sustained momentum against the market leaders. (4/6)
Video generation is now a global competition.
Models from Chinese AI firms (Kling, Hailuo, Wan, and Seedance) now collectively capture over 50% of usage. Meanwhile, Google’s other viral sensation, Veo-3, secured 24% share with its breakthrough native audio generation. (3/6)
Models from Chinese AI firms (Kling, Hailuo, Wan, and Seedance) now collectively capture over 50% of usage. Meanwhile, Google’s other viral sensation, Veo-3, secured 24% share with its breakthrough native audio generation. (3/6)
September 25, 2025 at 5:09 PM
Video generation is now a global competition.
Models from Chinese AI firms (Kling, Hailuo, Wan, and Seedance) now collectively capture over 50% of usage. Meanwhile, Google’s other viral sensation, Veo-3, secured 24% share with its breakthrough native audio generation. (3/6)
Models from Chinese AI firms (Kling, Hailuo, Wan, and Seedance) now collectively capture over 50% of usage. Meanwhile, Google’s other viral sensation, Veo-3, secured 24% share with its breakthrough native audio generation. (3/6)