ChatGPT Product Feed Format

The ChatGPT product feed format is the technical specification OpenAI published for merchants who want their products discoverable inside ChatGPT. It defines what fields to send, how to format them, and how to deliver updates so ChatGPT can accurately recommend products when users ask shopping questions.

The spec supports three file formats: JSONL (one product per line as JSON), CSV, and Parquet. JSONL is the reference format - most of the spec's examples and the richest attribute coverage assume JSONL. CSV is supported for simpler catalogs. Parquet is for high-volume enterprise merchants with millions of SKUs.

The current stable spec version is 2026-01-30 (announced by OpenAI on January 30, 2026). That version added support for product extensions, discount fields, and payment handler metadata. The spec lives on GitHub at developers.openai.com/commerce and evolves roughly once per quarter.

Once your feed is submitted, ChatGPT ingests it and the products become eligible for surfacing when users ask relevant shopping questions. Ingestion is typically daily; changes to price, inventory, or availability should be reflected in your feed within 24 hours to stay accurate.

Every product record must include a small set of required fields:

• id - a unique identifier stable across feed refreshes
• title - product name as a human would say it
• description - plain-language description, ideally 50-300 words
• price and price_currency - current price in ISO 4217 currency codes
• availability - in_stock, out_of_stock, preorder, or backorder
• link - canonical product URL on the merchant site
• image_link - primary product image (additional_image_link accepts an array of supporting images)

Beyond the required fields, the spec strongly recommends a rich set of structured attributes that materially improve discovery. These include brand, GTIN/MPN, category (Google product taxonomy), size, color, material, gender, age_group, condition, pattern, item_group_id (for variants), shipping, tax, product_highlight, and custom_label_0 through custom_label_4.

For specific verticals, the spec supports category-specific attributes. Apparel feeds should include size_system, size_type, and fit details. Consumer electronics need compatibility fields and spec sheets. Food and beverage items require nutrition_facts and ingredient data.

Merchants who ship only the required minimum often see products appear as text mentions rather than rich product cards. Rich cards (with image, price, and availability shown inline) require attribute completeness - and they drive materially better click-through rates.

There are three main paths to get products into the ChatGPT feed today:

1. Direct feed submission (via OpenAI). Merchants work directly with OpenAI's commerce team to submit feeds. This path is invite-based for large retailers and is how Walmart, Target, Best Buy, and other launch partners originally onboarded.

2. Platform syndication. If you run on Shopify, commercetools, or Salesforce Commerce Cloud, you can enable ChatGPT syndication through your platform. The platform generates a compliant feed from your catalog and maintains it. Shopify enabled this broadly in Q1 2026. Salesforce launched its pilot in April 2026 with Crocs and Pacsun as early partners.

3. Third-party integration. Paz.ai, an agentic commerce optimization platform, enriches your product data to meet ChatGPT's recommended attribute depth and distributes the resulting feed. This path suits mid-market brands that want attribute optimization applied before the feed ships, not just raw syndication.

Whichever path you pick, feeds must be refreshed on a regular cadence. Stale pricing or inventory data causes products to be de-prioritized or suppressed entirely. Most merchants target daily refresh; high-velocity SKUs may need hourly updates through the API.

Most feed quality problems fall into a handful of patterns:

Shallow titles. A title like "Black Shirt" will lose to "Men's Merino Wool Short-Sleeve Henley - Slim Fit, Charcoal Black". AI agents match specific query language to specific product language; the more descriptive your title, the more queries your product matches.

Missing Google product category. The Google product taxonomy (e.g. "Apparel & Accessories > Clothing > Shirts & Tops") is how ChatGPT maps free-text queries to product sets. Products without a category get fewer matches.

Vague descriptions. Marketing copy that tells a story but omits specs (material, fit, care, use cases) gives AI nothing to match on. The ideal description includes both the narrative and the spec sheet.

Incomplete variant grouping. The item_group_id field tells ChatGPT which products are variants of the same parent. Without it, your T-shirt in 5 colors might appear as 5 separate products competing against each other in rankings.

Stale pricing or inventory. Price mismatches between the feed and the merchant site are a hard de-ranking signal. Same for products shown as in-stock in the feed that 404 or show out-of-stock on the merchant site.

Missing shipping metadata. Shipping cost and delivery time are increasingly shown inline with product recommendations. Feeds that omit these lose to feeds that include them.