Model Catalog

Pixapi exposes multiple model families behind one API key. Pick a model id, pass it in the OpenAI-compatible request body, and keep the rest of your integration stable while you compare providers.

Image models

Image generation uses POST /v1/images/generations. Image editing uses POST /v1/images/edits when the model supports input images. Use n, size, and optional controls such as quality. For large outputs or slower models, submit through /v1/async/images/generations or /v1/async/images/edits, then poll GET /v1/tasks/{id}.

Model	Model id	Best for	Endpoints	Credits
Gemini 2.5 Flash Image	gemini-2.5-flash-image	Fast Gemini image generation and editing	Generate, edit	2
Gemini 3.1 Flash Lite Image	gemini-3.1-flash-lite-image	Lowest-cost Gemini 3.1 Flash Lite Image workflows optimized for velocity and scale	Generate, edit	2
Gemini 3.1 Flash Image Preview	gemini-3.1-flash-image-preview	Balanced Gemini image generation with aspect-ratio control	Generate, edit	from 4
Gemini 3 Pro Image Preview	gemini-3-pro-image-preview	Premium generation and edits with aspect-ratio control	Generate, edit	from 8
GPT Image 1.5	gpt-image-1.5	GPT image generation and editing with strong text rendering	Generate, edit	from 1
GPT Image 2	gpt-image-2	OpenAI quality tiers, custom sizes, prompt adherence	Generate, edit	from 1
GPT Image 2.5 Flare	gpt-image-2.5-flare	Speed-oriented generation, product variations, high-volume creation	Generate, edit	from 1
GPT Image 2.5 Sunburst	gpt-image-2.5-sunburst	Quality-oriented compositions, campaign assets, precise editing	Generate, edit	from 1
Gemini 3.1 Flash Preview 512	gemini-3.1-flash-image-preview-512	512px preview output	Generate, edit	4
Gemini 3.1 Flash Preview 2K	gemini-3.1-flash-image-preview-2k	2K preview output	Generate, edit	6
Gemini 3.1 Flash Preview 4K	gemini-3.1-flash-image-preview-4k	4K preview output	Generate, edit	8
Gemini 3 Pro Preview 2K	gemini-3-pro-image-preview-2k	Premium 2K output	Generate, edit	8
Gemini 3 Pro Preview 4K	gemini-3-pro-image-preview-4k	Premium 4K output	Generate, edit	16
Seedream 5.0 Pro	seedream-5-0-pro	Pro image generation and editing	Generate, edit	4
Seedream 5.0 Lite	seedream-5-0-lite	Lower-cost Seedream workflows	Generate, edit	3
Qwen Image 3.0	qwen-image-3.0	Qwen image generation and editing	Generate, edit	3
Wan 2.7 Image	wan2.7-image	Wan image generation and editing	Generate, edit	3
Wan 2.7 Image Pro	wan2.7-image-pro	Premium Wan image output	Generate, edit	7
FLUX.2 Pro	flux-2-pro	Resolution-controlled FLUX.2 output	Generate, edit	from 3
FLUX.2 Max	flux-2-max	Maximum-quality FLUX.2 output	Generate, edit	from 6
FLUX.2 Flex	flux-2-flex	Flexible FLUX.2 resolution tiers	Generate, edit	from 4
Grok Imagine 2.0 Ext	grok-imagine-2.0-ext	Text-to-image generation	Generate	2
Stable Diffusion 3.5 Large Turbo	stable-diffusion-3.5-large-turbo	Fast Stable Diffusion output	Generate, edit	4

Video models

Model	Model id	Best for	Endpoint	Credits
Veo	veo3.1-lite / veo3.1-fast / veo3.1-quality	Realistic motion and cinematic product clips	/v1/async/videos/generations	from 4/sec
Seedance	seedance-2 / seedance-2-fast / seedance-2-mini	Audio sync, first/last frames, multimodal references	/v1/async/videos/generations	from 4/sec
Kling	kling-3.0-turbo / kling-v3 / kling-v3-omni	Expressive motion and subject control	/v1/async/videos/generations	from 9/sec
Wan	wan2.6 / wan2.6-flash	Creative scenes and camera transitions	/v1/async/videos/generations	from 5/sec
Grok Video	grok-video-3 / grok-video-1.5-preview	Short clips from text or image	/v1/async/videos/generations	from 5/sec
HappyHorse	happyhorse-1.1	Text/image/reference video generation	/v1/async/videos/generations	from 13/sec

Newly available models

Field	model	Endpoint
qwen-image-3.0-pro	qwen-image-3.0-pro	/v1/images/generations
qwen-image-2.0	qwen-image-2.0	/v1/images/generations
qwen-image-2.0-pro	qwen-image-2.0-pro	/v1/images/generations
z-image-turbo	z-image-turbo	/v1/images/generations
wan2.6-t2v	wan2.6-t2v	/v1/async/videos/generations
wan2.6-i2v	wan2.6-i2v	/v1/async/videos/generations
wan2.6-i2v-flash	wan2.6-i2v-flash	/v1/async/videos/generations
wan2.7-t2v	wan2.7-t2v	/v1/async/videos/generations
wan2.7-i2v	wan2.7-i2v	/v1/async/videos/generations
wan2.7-r2v	wan2.7-r2v	/v1/async/videos/generations
wan2.7-videoedit	wan2.7-videoedit	/v1/async/videos/generations
wan3.0-video	wan3.0-video	/v1/async/videos/generations
wan3.0-video-prime	wan3.0-video-prime	/v1/async/videos/generations

Credit deduction

Gemini image requests are billed by selected model and output tier.

Model id	Credits / image
gemini-2.5-flash-image	2
gemini-3.1-flash-lite-image	2
gemini-3.1-flash-image-preview-512	4
gemini-3.1-flash-image-preview	4
gemini-3.1-flash-image-preview-2k	6
gemini-3.1-flash-image-preview-4k	8
gemini-3-pro-image-preview	8
gemini-3-pro-image-preview-2k	8
gemini-3-pro-image-preview-4k	16

GPT Image 2, GPT Image 2.5 Flare, and GPT Image 2.5 Sunburst are billed by output size tier and quality. quality=auto is billed as high, and size=auto defaults to the 1K tier.

Size tier	Long edge	low	medium	high / auto
1K	<= 1536px	1	4	14
2K	<= 2048px	2	17	67
4K	<= 3840px	4	34	133

Video models are billed as n × seconds × rate(resolution). See each model page for allowed seconds / resolution values.

Video generation is async-only. Use /v1/async/videos/generations and the Async Media Tasks flow for all video integrations.

Model / tier	Pixapi credits
veo3.1-lite 720P / 1080P	4/sec / 7/sec
veo3.1-fast 720P / 1080P / 4K	8/sec / 10/sec / 24/sec
veo3.1-quality 720P·1080P / 4K	32/sec / 48/sec
seedance-2-mini 480P / 720P	4/sec / 8/sec
seedance-2-fast 480P / 720P	6/sec / 13/sec
seedance-2 480P / 720P / 1080P / 4K	8/sec / 16/sec / 38/sec / 78/sec
kling-3.0-turbo 720P / 1080P	12/sec / 15/sec
kling-v3 720P / 1080P	11/sec / 14/sec
kling-v3 (audio: false) 720P / 1080P	9/sec / 12/sec
kling-v3-omni 720P / 1080P	9/sec / 12/sec
kling-v3-omni (reference video via video_list) 720P / 1080P	11/sec / 14/sec
wan2.6-flash 720P / 1080P	5/sec / 8/sec
wan2.6 720P / 1080P	9/sec / 15/sec
grok-video-3 480P / 720P	5/sec / 7/sec
grok-video-1.5-preview 480P / 720P	8/sec / 14/sec
happyhorse-1.1 720P / 1080P	13/sec / 18/sec

Choosing a model

• Use gemini-3.1-flash-lite-image for the fastest and lowest-cost Gemini 3.1 Flash Lite Image workflows.
• Use gemini-2.5-flash-image for legacy image-generation quick image output and editing workflows.
• Use gemini-3.1-flash-image-preview when you need a balanced Gemini preview model with aspect-ratio control.
• Use gemini-3-pro-image-preview when quality matters more than cost.
• Use gpt-image-2, gpt-image-2.5-flare, or gpt-image-2.5-sunburst when prompt adherence, typography, custom size, or layout precision matters.
• Use veo3.1-lite, veo3.1-fast, or veo3.1-quality when the output needs motion, camera direction, and video timing.
• Use seedance-2 when you need audio sync, first/last frames, or multimodal references.
• Use kling-v3 / kling-v3-omni for Kling clips with subject control, or kling-3.0-turbo for the turbo pipeline.
• Use wan2.6 / wan2.6-flash, grok-video-3, or happyhorse-1.1 for additional video providers on the same async endpoint.

Stable integration pattern

The endpoint usually stays the same for a media type. Switching models is normally a request-body change:

{
  "model": "gemini-3-pro-image-preview",
  "prompt": "A clean product hero image for a developer API platform",
  "n": 1,
  "size": "1:1"
}

Legacy image-generation fields are separated under Legacy transition format.