Positioning
Gemini 2.5 Flash Image is a multimodal model optimized for fast image understanding, generation, and editing, balancing cost and performance. (docs.cloud.google.com)
Release and availability
Google announced general availability on October 2, 2025. The GA release added aspect-ratio controls, image-only responses, regional endpoints, batch prediction, generation from multiple reference images, and improved multi-turn editing. The earlier preview was announced on August 26, 2025. (docs.cloud.google.com)
The model is now deprecated. Google lists March 15, 2027 as its retirement date and recommends migrating to Gemini 3.1 Flash-Lite Image. (docs.cloud.google.com)
Capabilities and uses
The model accepts text and images and can return text and images, including interleaved responses. It supports generating images from multiple references and conversational, multi-turn image editing. Potential uses include marketing visuals, combining product images, and iterative creative editing. (docs.cloud.google.com)
Limits
In Google Cloud's model documentation, the context window and maximum output are each listed as 32,768 tokens. Audio and video are not supported. The documented limits include three input images and up to ten output images per prompt; file-size and format restrictions also apply. Context caching, structured output, function calling, and grounding are listed as unsupported on that platform. Availability and limits can differ by platform. (docs.cloud.google.com)
Pricing
Gemini Developer API paid tier, USD; checked November 17, 2026. These are Developer API prices, not a Vertex AI price quote. The model's pricing page says text input and output follow Gemini 2.5 Flash pricing. (aistudio.google.com)
- Standard: text or image input $0.30 per million tokens; text output $2.50 per million tokens. Image output is $30 per million image tokens: an image up to 1024×1024 consumes 1,290 tokens, equivalent to $0.039 per image.
- Batch: text or image input $0.15 per million tokens; text output $1.25 per million tokens; image output $0.0195 per image.
- Flex: text or image input $0.15 per million tokens; text output $1.25 per million tokens; image output $0.0195 per image.
- Priority: text or image input $0.54 per million tokens; text output $4.50 per million tokens; image output $0.0702 per image.
The image pricing page lists no free tier for these modes. Image-per-item equivalents are subject to the output-token and resolution conditions stated on the pricing page. (aistudio.google.com)