Profile

GPT‑5.4 Mini is a fast, affordable general‑purpose model designed for production assistants, coding support, document analysis, and multimodal reasoning. With a 400k‑token context window, it handles complex inputs and scalable workflows with strong reliability. This bot supports optional parameters for additional customization.

GPT‑5.4 Nano is the fastest and most cost‑efficient model in the GPT‑5 family, built for high‑volume tasks such as summarization, categorization, extraction, and lightweight multimodal workflows. It supports native vision and a 400k‑token context window for efficient large‑scale processing. This bot supports optional parameters for additional customization.

A smarter, more precise version of GPT-5.4 that leverages additional compute to think harder and provide consistently better answers. Designed to tackle your toughest problems, this model operates with the highest reasoning capability to ensure maximum accuracy on complex tasks. This bot supports optional parameters for additional customization.

Enabled by Cerebras’s custom high-performance chips, GPT 5.3 Codex Spark is OpenAI's lightweight coding model optimized for fast code generation (~1000 tokens / second). Supports a 128k context window. Poe users get early research preview access to GPT-5.3-Codex-Spark at near-zero cost. This bot supports optional parameters for additional customization.

GPT-5.3 Instant focuses on making everyday conversations smoother, more accurate, and more directly helpful. It reduces hallucinations, unnecessary refusals, and long defensive caveats while producing clearer answers and better-synthesized results when using web information. It’s designed to feel faster and more natural in normal chats rather than adding new capabilities or heavy reasoning features. This bot supports optional parameters for additional customization.

GPT-5.4 is the most capable AI model from OpenAI, built for advanced real-world tasks across coding, computer use, deep research, complex document understanding, and multi-step problem solving. It outperforms previous versions on agentic workflows and tool use, delivering stronger reasoning, higher accuracy, and more reliable results on complex tasks. This bot supports optional parameters for additional customization.

GPT‑5.3‑Codex excels in software development. It understands complex codebases, provides accurate completions, explains algorithms, and assists with debugging across modern programming languages. Designed for developers, it elevates productivity and supports full‑stack coding workflows with precision. Supports 400k tokens of input context. This bot supports optional parameters for additional customization.

GPT‑5.2‑Codex extends GPT‑5.2’s capabilities for software development. It understands complex codebases, provides accurate completions, explains algorithms, and assists with debugging across modern programming languages. Designed for developers, it elevates productivity and supports full‑stack coding workflows with precision. Supports 400k tokens of input context. Optional parameters: Set reasoning effort: Select from `low`, `medium`, `high`, `xhigh`. This is set to `medium` by default.

OpenAI's frontier image generation model in ChatGPT as of December 2025, offering exceptional prompt adherence, world knowledge, precise edits, facial preservation, level of detail, and overall quality with improved latency/generation times. It supports editing, restyling, and combining images attached to the latest user query. For a conversational image generation and editing experience use: https://poe.com/GPT-5.2 Optional Parameters: Set aspect ratio, with options 3:2, 1:1 and 2:3. Set quality to low, medium and high. Default is set to high. Enable use mask by toggling it on or by typing 'use_mask' in the prompt. This option is turned off by default. Disable high fidelity by toggling it off or by typing 'use_high_fidelity'. This option is turned on by default.

A powerful reasoning model that is ideal for your most complex, highest difficulty tasks. On x-high reasoning effort, scores a 90.5% on ARC-AGI-1 benchmark, an incredibly difficult problem-solving benchmark where humans score 100%. Note: the model can take up to 30 minutes to think through a problem and is quite expensive. Supports 400k tokens of context and native vision. This bot supports optional parameters for additional customization.