Skip to content
Patient Copilot Help Center

GPT-5 in Patient Copilot Workflows

Harness the power of cutting‑edge AI directly inside your automations. GPT‑5 in Workflows lets you embed OpenAI’s newest language models, GPT‑5, GPT‑5 Mini, GPT-5.1 and GPT‑5 Nano into Patient Copilot steps for smarter, faster, and cost‑efficient task execution. This guide explains what the feature is, why it matters, its costs, and the exact steps to get started. * * * ## What is GPT 5 in Workflows? GPT‑5 in Workflows is Patient Copilot’s latest integration of OpenAI’s GPT‑5 family, enabling any workflow to generate or transform text with unprecedented accuracy and speed. By selecting the GPT action and choosing a GPT‑5 variant, you unlock longer context windows, richer reasoning, and lower latency compared to earlier models. * * * ## Key Benefits of GPT 5 in Workflows Intelligent automation gets real‑time, enterprise‑grade language understanding. - Speed: Accelerated processing for near real‑time execution, reducing wait times for customers. - Reliability: Consistent, high‑quality outputs thanks to GPT‑5’s refined reasoning abilities. - Flexibility: Three model tiers let you balance performance and budget without rewriting workflows. - Simplicity: Native, click‑to‑configure action keeps integration and maintenance effortless. * * * ## GPT 5 Models, Pricing, and Token Math Choose the tier that matches your volume and performance needs—pay only for the tokens you consume. | Model | Best For | Max Context Window | Relative Latency* | Input Cost per 1M Tokens | Output Cost per 1M Tokens | | --- | --- | --- | --- | --- | --- | | GPT‑5 | Long‑form reasoning, document analysis, high‑stakes copy | 256k | ◼︎◼︎◼︎◼︎ (slower) | | | | GPT‑5 Mini (default) | General email drafting, chat replies, marketing copy | 128k | ◼︎◼︎◼︎ (balanced) | | | | GPT‑5 Nano | High‑volume classification, short replies, light summarization | 64k | ◼︎◼︎ (fastest) | | | | GPT-5.1 | Better Instruction following over other OpenAI models with a warmer, more conversational personality. | 128k | | | | IMPORTANT: Pricing mirrors OpenAI’s published rates and is billed via your Patient Copilot AI wallet. Both agency markup and client rebilling apply automatically. ### Token Math Mastering token math lets you forecast AI costs accurately and avoid billing surprises. Patient Copilot bills GPT‑5 usage exactly as OpenAI does, by counting input tokens (your prompt + context) and output tokens (the model’s response). One token is roughly four characters of English text. Charges are prorated to the nearest thousandth of a million tokens (0.001 M). #### Example:- A 400-word email (~2,000 characters ≈ 500 tokens) sent to GPT-5 Mini costs: - Input: 500 tokens × / 1M =