GPT Image 2.6 went live on Nov 4 in ChatGPT, Codex and the API simultaneously. API access itself is simple — two model IDs, two endpoints — but several limits are easy to trip over: Image API only, GIF needs preview access, SVG is API-only, and 2.6 has no Batch pricing. This article covers the API, Codex, OpenRouter and third-party routes.
Model IDs: gpt-image-2.6-sunburst and gpt-image-2.6-flare. Only the Image API's POST /v1/images/generations and POST /v1/images/edits; Responses API image tools, Chat Completions and Batch API are all marked unsupported. Quality tiers: low/medium/high/xhigh/max/auto. New parameters: complexity (low/medium/high, default high), GIF's output_format: "gif" and frame_count, SVG's output_format: "svg" and svg.model. No free tier on the API. Rate-limit numbers are unpublished — the model page has no tier table, only "varies by usage tier and account".
GIF requires GIF preview access for the chosen model; GIF generation in ChatGPT is still rolling out gradually, and not all accounts have it yet. SVG is API-only (no SVG export in ChatGPT): set output_format: "svg" on the generation endpoint, n must be 1; the editing endpoint doesn't support SVG output, and SVGs can't be used as editing input. SVG is billed as two parts: the reference image at image-model rates + the author model at its token rates, with no fixed per-image price. See our GIF & SVG article for hands-on results.
The announcement says globally available on all tiers; image generation counts against the same usage quota as normal conversation, and per OpenAI's Codex pricing FAQ, turns with image generation consume quota 3–5x faster than comparable text-only turns (depending on image quality and size). The Codex CLI ships a built-in $imagegen skill, with generated images saved by default to ~/.codex/generated_images/ — that detail comes from a gpt-image-2-era article; Codex-specific behavior for 2.6 beyond the announcement and the FAQ multiplier has not been separately verified.
openai/gpt-image-2.6-sunburst and openai/gpt-image-2.6-flare, listed Nov 4, sole provider OpenAI (no routing); prices match the official ones ($8/$30 per 1M tokens); EU-region routing not supported yet. OpenRouter's model description says 2.6 is "about 50% faster than GPT Image 2.5" — that's OpenRouter's wording; the official announcement names no comparison baseline.
Replicate (per-image: low $0.05, medium $0.09, high $0.128, max $0.50; GIF and SVG per output token), fal (live on launch night, $30/1M output tokens), Runware (both models on Nov 5), BudgetPixel ($0.12/image retail), SYNTX.AI, Treza, LaoZhang API (own VIP model at a fixed $0.03/call — aggregator pricing, not OpenAI's). Recraft Studio (added Nov 5): Sunburst available at default settings on the free plan, Flare and all quality tiers require a paid plan; 1K or 2K; credits 4–57 (default 10).
ChatGPT launched globally on all tiers including free — multiple reports and hands-on tests confirm free accounts can use it (the Medium tester used a free account). But OpenAI publishes no fixed image count for any tier. The only number is a Medium author's single-person test: a free account hit the cap after ~8 operations (images, GIFs and edits combined), with a prompt to retry after 24 hours (counted from the first operation). That's a single-person test, not an official quota. Any claim of "the free tier gives you X images a day" is not credible unless it cites a source.
Reference: ofox — GPT Image 2.6 API Pricing (rewritten and organized by ModelBrief; facts per the source)