# GPT Image 2.6 Flare - **Guide status: unavailable** - **Catalog model ID**: `gpt-image-2.6-flare` - **Lifecycle**: listed (source: model-scene.releaseStatus/preRelease/isShow; not an inference availability test) - **max_input_tokens**: unknown - **platform_max_input_tokens**: unknown (source missing or nonpositive; not parsed from marketing text) - **provider_context_tokens**: 400000 (source: Data API models.context_length, uniquely matched provider SKU; separate from platform input limits) - **Context source**: model-scene.maxInTokenNumber, tokens; platform-published input limit, not an independently verified provider maximum - **Editorial facts**: marketing summaries are excluded; use the structured context, pricing and request fields below - **Catalog model ID**: `gpt-image-2.6-flare` (not a confirmed request model value) - **Scene**: `text-to-image` - **Base URL**: not confirmed by this guide's sources - **Endpoint**: not confirmed by this guide's sources - **Request model value**: not confirmed by this guide's sources - **Authentication**: not confirmed by this guide's sources - **API availability**: not tested; missing documentation does not establish whether inference is supported This is a discovery record, not an integration guide. Its sources do not provide enough model-specific Quick Start or usable form/CMS request data to document this scene. This describes documentation coverage, not a model outage or retirement. Do not infer an API contract from this catalog ID, page URL or another model's guide. Choose a documented candidate or contact support before sending an inference request. ## Continue here - [Model page](https://gptproto.com/model/openai/gpt-image-2.6-flare) - [API documentation index](https://docs.gptproto.com/llms.txt) - [Model discovery index](https://gptproto.com/llms.txt) - [Other models from this provider](https://gptproto.com/llms/providers/openai/llms.txt) ## Pricing Billing shape: `per_token_image`. Platform USD quotes already include the discount. Run rows are complete request totals for their listed parameters. Second/token rows are unit rates. Pricing controls describe billing, not the server's accepted API parameters. ### Token rates (4 published rows) - **Cached Input** — $1.9 per 1M tokens; USD; unit rate - **Text Input** — $4.75 per 1M tokens; USD; unit rate - **Image Input** — $7.6 per 1M tokens; USD; unit rate - **Image Output** — $28.5 per 1M tokens; USD; unit rate - Image price depends on actual image/text tokens; this is not a fixed per-image tariff. Prices may change. The model page always shows the live price: https://gptproto.com/model/openai/gpt-image-2.6-flare