model field.
The exact set your key can call, and each model’s supported parameters, is returned by
GET /v1/models. For per-model rates, see deepshi.ai.Deepshi models
Deepshi’s own image models, running on Deepshi GPUs.
Deepshi Banana 2
deepshi-banana-pro-2 · Prompt 10KDeepshi’s flagship in-house text-to-image, tuned for realism across styles, with quality and resolution controls up to 8MP. DimensionsDeepshi Image 2
deepshi-image-2 · Prompt 10KSecond-generation in-house model for text-to-image and multi-reference editing of up to five images. Dimensions EditingThird-party models
Leading image models from across the industry, through the same endpoint, key, and balance. Recently added models appear first.
GPT Image 2.5
gpt-image-2.5 · Prompt 32KOpenAI’s newest GPT Image model, with a clearer step up in detail at the default quality tier. Preset sizes Editing
Qwen-Image 2.1
qwen-image-2.1 · Prompt 5KAlibaba’s newest 2.x image model, with strong in-image text and instruction following in English and Chinese. Preset sizes Editing
Wan 2.7 Pro Image
wan-2.7-pro-image · Prompt 2KThe higher-fidelity tier of Alibaba’s Wan 2.7 image model, generating and editing from reference images. Preset sizes EditingWan 2.7 Image
wan-2.7-image · Prompt 2KAlibaba’s Wan-family image model, generating from text and editing from reference images at a low price. Preset sizes EditingLuma Uni-1
luma-uni-1 · Prompt 6KLuma’s agentic image model with strong typography and stylized output. Generations take longer than typical image models. Aspect ratio Editing
Grok Imagine 2.0
grok-imagine-2 · Prompt 8KThe second generation of xAI’s Grok Imagine, generating and editing at 1K or 2K with a selectable quality. Resolution EditingQwen-Image 3
qwen-image-3 · Prompt 5KAlibaba’s latest image model, sharpening in-image text rendering in English and Chinese. Preset sizes EditingFIBO Gen 1.5
fibo-gen-1.5 · Prompt 10KBria’s high-fidelity generator with dependable typography, at 1MP or 4MP. Resolution
Kling Image O3
kling-image-o3 · Prompt 2.5KKuaishou’s flagship image model, generating and editing at up to 4K with multiple reference images. Resolution EditingKling Image V3
kling-image-v3 · Prompt 2.5KA budget Kling tier at 1K and 2K, with single-image editing. Resolution Editing
Reve 2.1
reve-2.1 · Prompt 4KReve’s model for exact prompt adherence and reliable in-image text, across a wide range of aspect ratios. Aspect ratio Editing
Krea 2 Turbo
krea-2-turbo · Prompt 5KKrea’s fast text-to-image model with a polished, design-oriented look. Preset sizes
Ernie Image
ernie-image · Prompt 10KBaidu’s text-to-image model with eleven size presets and adjustable inference steps. Preset sizes
Cosmos 3 Super
cosmos-3-super · Prompt 4KNVIDIA’s model for physically grounded scenes with realistic lighting and geometry. Preset sizesQwen-Image 2
qwen-image-2 · Prompt 10KAlibaba’s model with strong text rendering, in English and Chinese. Preset sizes Editing
HiDream-O1
hidream-o1 · Prompt 10KAn open model for generation, editing, and reference-based personalization. Preset sizes Editing
Seedream 5 Pro
seedream-v5-pro · Prompt 10KByteDance’s flagship Seedream, strong at dense text and structured layouts. Preset sizes Editing
FLUX.2 Turbo
flux-2-turbo · Prompt 10KThe fastest, lowest-cost tier of Black Forest Labs’ FLUX.2 family. Dimensions EditingFLUX.2 Flex
flux-2-flex · Prompt 10KFLUX.2 with adjustable steps and guidance, and up to ten reference images. Dimensions Editing
Nano Banana 2 Lite
nano-banana-2-lite · Prompt 50KThe fast, low-cost tier of Nano Banana 2, at 1K. Aspect ratio EditingGPT Image 1 Mini
gpt-image-1-mini · Prompt 32KA compact, low-cost GPT Image tier with a selectable quality. Preset sizes EditingNano Banana 2
nano-banana-2 · Prompt 50KGoogle’s fast, prompt-faithful generator with flexible aspect ratios, up to 4K. Resolution EditingGPT Image 1.5
gpt-image-1.5 · Prompt 32KOpenAI’s image model, with strong prompt adherence and text rendering. Preset sizes EditingSeedream 4.5
seedream-4.5 · Prompt 10KByteDance’s photorealistic generator with flexible preset sizes up to 4K. Preset sizes EditingSeedream 5 Lite
seedream-5-lite · Prompt 10KA lighter, faster Seedream variant for quick high-resolution generations. Preset sizes EditingGrok Imagine
grok-imagine · Prompt 8KxAI’s image model for fast, stylistic generations across many aspect ratios. Aspect ratio EditingGrok Imagine Quality
grok-imagine-quality · Prompt 8KThe higher-resolution Grok Imagine tier, for crisper detail at 2k. Resolution EditingNano Banana Pro
nano-banana-pro · Prompt 50KThe pro tier of Nano Banana, for higher-fidelity detail and large 4K renders. Resolution EditingGPT Image 2
gpt-image-2 · Prompt 32KOpenAI’s GPT Image 2, with sharp detail and a selectable quality tier. Preset sizes EditingFLUX.2 Pro
flux-2-pro · Prompt 10KBlack Forest Labs’ high-fidelity generator with precise pixel-dimension control. Dimensions Editing
Ideogram V4
ideogram-v4 · Prompt 10KIdeogram’s model, strong at typography and graphic design, with a selectable rendering speed. Dimensions Editing