Supported models

Name a model by its ID when you generate through the AI Gateway.

Provider	Model	Model ID	Makes	Starts from
OpenAI	GPT Image 2.5 Flare	`openai/gpt-image-2.5-flare`	Images	Text, images
OpenAI	GPT Image 2.5 Sunburst	`openai/gpt-image-2.5-sunburst`	Images	Text, images
OpenAI	GPT Image 2.6 Flare	`openai/gpt-image-2.6-flare`	Images, SVG	Text, images
OpenAI	GPT Image 2.6 Sunburst	`openai/gpt-image-2.6-sunburst`	Images, SVG	Text, images
Google	Nano Banana 2.1	`google/nano-banana-2.1`	Images	Text, images
Google	Gemini Omni Flash 1.2	`google/gemini-omni-flash-1.2`	Video	Text, images, video
ByteDance	Seedream 5 Pro	`bytedance/seedream-5-pro`	Images	Text, images
ByteDance	Seedance 2.5	`bytedance/seedance-2.5`	Video	Text, images, audio, video
ElevenLabs	Eleven v4	`elevenlabs/eleven-v4`	Speech	Text
Krea	Krea 3	`krea/krea-3`	Images	Text, images

Options

Each model has its own options. An option shown with a value, such as quality=high, defaults to that value.

Model	Options
GPT Image 2.5 Flare, GPT Image 2.5 Sunburst	`prompt`, `images`, `quality=high`, `size=auto`, `background=auto`, `output_format=png`
GPT Image 2.6 Flare, GPT Image 2.6 Sunburst	`prompt`, `image_urls`, `mask_url`, `markup_image_url`, `image_size`, `background=auto`, `quality=high`, `reasoning_effort=high`, `num_images=1`, `output_format=png`, `output_compression`, `frame_count`, `frame_duration_ms`
Nano Banana 2.1	`prompt`, `image_input`, `aspect_ratio=1:1`, `image_size=2K`
Gemini Omni Flash 1.2	`operation=generate`, `prompt`, `image_url`, `end_image_url`, `image_urls`, `reference_video_urls`, `video_url`, `aspect_ratio`, `resolution`, `duration`
Seedream 5 Pro	`prompt`, `image`, `size=2K`
Seedance 2.5	`prompt`, `image`, `last_frame_image`, `reference_images`, `reference_videos`, `reference_audios`, `duration=5`, `resolution=720p`, `aspect_ratio=adaptive`, `generate_audio=true`, `seed`
Eleven v4	`text`, `voice=jonathan`, `stability`, `similarity_boost`
Krea 3	`prompt`, `image_urls`, `image_size=auto`, `reasoning_level=medium`, `negative_prompt`, `seed`, `output_format=png`, `regional_edit`, `regions`

To see the values and limits a model accepts, ask your connected agents:

Show me the options for GPT Image 2.6 Sunburst (openai/gpt-image-2.6-sunburst)
through the AI Gateway, with the values each one accepts.

For API clients, see List models and Get a model.