ChatGPT Images 2.0
OpenAI- Cost
- 1 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, quality
Models · 145+
Every frontier AI model — one canvas, one bill.
Beemm Vision wires 145+ AI models from 22 frontier providers — 91 image and 54 video — into one collaborative canvas. Switch model with one click, no API key juggling, pay from one shared credit balance.
Catalog highlights
145+
Models
91
Image
54
Video
22
Providers
The models, one by one
What each one does better than the rest, which variants run here, and the questions worth asking before choosing.
- Nano BananaGoogle
Use Google's Nano Banana 2.1, Nano Banana 2 and Pro image models on one canvas: legible in-image text, editing from up to 14 references, up to 4K.
- KlingKuaishou
Generate video with Kling 4.0, V3 and O3 4K: text, image or reference to video, up to 30 seconds, multi-shot sequences and generated audio.
- SeedreamByteDance
Generate with ByteDance's Seedream and Seedream 5 Pro: photographic rendering, instruction-based editing, output up to 4K, on one canvas.
- FLUXBlack Forest Labs
Use FLUX 3 from Black Forest Labs: images up to 4K, FLUX.3 Klein and Klein Base, 5 to 20 second videos at 1080p with a draft mode, and FLUX.2 Pro.
- Grok ImaginexAI
Use xAI's Grok Imagine: 2.0 and Pro images up to 2K, Video 1.5 up to 1080p, plus video extension and editing — all in one canvas, on one balance.
- SeedanceByteDance
Generate video with ByteDance's Seedance 2.5, 2 Reference and 1.5 Pro: up to 30 seconds, 30 reference images, generated audio.
- LumaLuma
Generate and edit images with Luma Uni-1 and Uni-1 Max, one unified model, and 5 or 10 second videos with Luma Ray 3.2, inside a multi-model canvas.
- RecraftRecraft
Recraft V4.1 Pro generates images and, above all, VECTOR output: logos, icons, pictograms. The only model in the catalogue that returns editable curves.
- WanAlibaba
Generate video with Alibaba's Wan 3.0, 3.0 Prime, 2.7 and 2.6 Flash: up to 30 seconds, 10 reference images, 5 reference clips, reference audio.
- GPT ImageOpenAI
Use OpenAI's GPT Image 2 and GPT Image 1.5 without a ChatGPT subscription: generation, editing and eight formats, on a balance shared with the whole catalogue.
- Hunyuan ImageTencent
Generate with Tencent's Hunyuan Image: text-to-image and editing, output up to 4K, eight formats — in a canvas that gathers the whole catalogue.
- MiniMax H3MiniMax
Generate video with MiniMax H3, from the maker of Hailuo AI: 5 to 15 seconds up to 4K, VHS or pixel-art styles, video extension and scene insertion.
- Qwen ImageAlibaba
Generate and edit images with Alibaba's Qwen Image, versions 2, 2 Pro and 3, in generation and editing alike, in a multi-model canvas.
- IdeogramIdeogram
Use Ideogram V4.5 and V4: image generation from text, editing with a mask and reference images, plus the Fast and Instant versions — in one canvas.
- HiggsfieldHiggsfield
Run Higgsfield models with no Higgsfield subscription: Genjutsu motion transfer, Marketing Studio, Cinema Studio and Soul — in one canvas.
- Marigold V2Huawei
Create the depth map of an image with Marigold V2: one image in, no prompt, a colourised PNG depth map out — in the canvas.
- Meta Muse ImageMeta
Use Meta Muse Image: image generation from text and editing from one to ten reference images, in one multi-model canvas.
Powered by every frontier provider
Already on another tool?
See how Beemm Vision's full catalog stacks up against the most-used generative tools — feature by feature, no marketing fluff.
Text-to-image models
46 modelsGenerate from a prompt alone. Pick a model that fits your aesthetic — fast iterations on cheaper models, hero shots on the premium ones.
T2I
Flux 2 Pro
Black Forest Labs- Cost
- 6 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
FLUX 3 Image (Text to Image)
Black Forest Labs- Cost
- 6 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
FLUX.3 Klein (Text to Image)
Black Forest Labs- Cost
- 1 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
FLUX.3 Klein Base (Text to Image)
Black Forest Labs- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
GPT Image 1.5
OpenAI- Cost
- 2 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, quality, background
GPT Image 2.5 Flare
OpenAI- Cost
- 6 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, quality, background
GPT Image 2.5 Sunburst
OpenAI- Cost
- 6 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, quality, background
Grok Imagine
xAI- Cost
- 2 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Grok Imagine 2.0
xAI- Cost
- 6 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, quality
Grok Imagine Pro (Text to Image)
xAI- Cost
- 5 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Hunyuan Image (Text to Image)
Tencent- Cost
- 10 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Ideogram V4 (Text to Image)
Ideogram- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, rendering_speed, expansion_model
Ideogram V4 Fast
Ideogram- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, rendering_speed, expansion_model
Ideogram V4 Instant
Ideogram- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, expansion_model
Ideogram V4.5 (Text to Image)
Ideogram- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, quality
Kling Image (Text to Image)
Kuaishou- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Kling Image o3 (Text to Image)
Kuaishou- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Krea 2
Krea- Cost
- 6 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, creativity
Krea 2 Medium
Krea- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, creativity
Krea 2 Turbo
Krea- Cost
- 1 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, acceleration, seed
Krea 3 (Text to Image)
Krea- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Luma Uni-1 (Text to Image)
Luma AI- Cost
- 5 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Luma Uni-1 Max (Text to Image)
Luma AI- Cost
- 11 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Meta Muse Image (Text to Image)
Meta- Cost
- 1 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Nano Banana 2 (Text to Image)
Google DeepMind- Cost
- 8 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, thinking_level, enable_web_search
Nano Banana 2 Lite (Text to Image)
Google DeepMind- Cost
- 5 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, thinking_level
Nano Banana 2.1 (Text to Image)
Google DeepMind- Cost
- 7 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Nano Banana Lite (Text to Image)
Google DeepMind- Cost
- 5 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, thinking_level
Nano Banana Pro (Text to Image)
Google DeepMind- Cost
- 15 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, enable_web_search
Qwen Image 2
Alibaba- Cost
- 4 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, negative_prompt, seed
Qwen Image 2 Pro
Alibaba- Cost
- 8 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, negative_prompt, seed
Qwen Image 3
Alibaba- Cost
- 4 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, negative_prompt, seed
Qwen Image Max (Text to Image)
Alibaba- Cost
- 8 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Recraft V4.1
Recraft- Cost
- 4 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, colors, background_color
Recraft V4.1 Flash
Recraft- Cost
- 1 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, colors, background_color
Recraft V4.1 Pro
Recraft- Cost
- 25 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, colors, background_color
Recraft V4.1 Utility
Recraft- Cost
- 4 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, colors, background_color
Recraft V4.1 Utility Pro
Recraft- Cost
- 21 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, colors, background_color
Reve 2.1 (Text to Image)
Reve- Cost
- 25 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Seedream (Text to Image)
ByteDance- Cost
- 4 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Seedream 5 Flash (Text to Image)
ByteDance- Cost
- 3 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Seedream Lite (Text to Image)
ByteDance- Cost
- 4 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Seedream Pro (Text to Image)
ByteDance- Cost
- 7 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt
Soul 2
Higgsfield- Cost
- 2 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, style_id, custom_reference_id, enhance_prompt, batch_size
Soul Cinema
Higgsfield- Cost
- 10 cr.
- Inputs
- 0 img
- Outputs
- 1 img
Parameters: prompt, custom_reference_id, enhance_prompt, batch_size
Image-to-image (edit & extend)
42 modelsBring your own reference, then transform it: edit, restyle, extend, mask. The lineup is brutally complete — every frontier editor in one place.
ChatGPT Images 2.0 Edit
OpenAI- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, quality
FLUX 3 Image
Black Forest Labs- Cost
- 6 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
FLUX.2 Pro Edit
Black Forest Labs- Cost
- Billed on the source image's size · from 6 cr. (1 MP source image)
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
FLUX.3 Klein
Black Forest Labs- Cost
- Billed on the source image's size · from 2 cr. (1 MP source image, 1K)
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
FLUX.3 Klein Base
Black Forest Labs- Cost
- Billed on the source image's size · from 6 cr. (1 MP source image, 1K)
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
GPT Image 1.5 (Edit)
OpenAI- Cost
- 2 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, mask_image_url, quality, background, input_fidelity, output_format
GPT Image 2.5 Flare Edit
OpenAI- Cost
- 6 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, mask_url, quality, background
GPT Image 2.5 Sunburst Edit
OpenAI- Cost
- 6 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, mask_url, quality, background
Grok Edit
xAI- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Grok Imagine 2.0 (Edit)
xAI- Cost
- 7 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, quality
Grok Imagine Pro
xAI- Cost
- 5 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
HiDream O1 Image
HiDream.ai- Cost
- 5 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Hunyuan Image
Tencent- Cost
- 10 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Ideogram V4
Ideogram- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, rendering_speed, expansion_model
Ideogram V4.5
Ideogram- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, mask_url, quality, edit_precision
Kling Image V3
Kuaishou- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Kling Omni 3
Kuaishou- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Krea 2 (Style)
Krea- Cost
- 7 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, creativity
Krea 2 Medium (Style)
Krea- Cost
- 4 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, creativity
Krea 2 Turbo (Style)
Krea- Cost
- 1 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, acceleration, style_scale, seed
Krea 3
Krea- Cost
- Billed on the number of reference images · from 5 cr. (1 reference image, 1K)
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Luma Uni-1
Luma AI- Cost
- 5 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Luma Uni-1 Max
Luma AI- Cost
- 11 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Marigold V2
Huawei- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: image
Marketing Studio 2.0 Alpha
Higgsfield- Cost
- 6 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, quality, preset_id, enhance_prompt, moderation
Marketing Studio 2.5 Flare
Higgsfield- Cost
- 2 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, quality, preset_id, enhance_prompt, moderation
Marketing Studio 2.5 Sunburst
Higgsfield- Cost
- 2 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, quality, preset_id, enhance_prompt, moderation
Meta Muse Image
Meta- Cost
- 1 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Nano Banana 2
Google DeepMind- Cost
- 8 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, seed
Nano Banana 2 Lite
Google DeepMind- Cost
- 5 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, seed
Nano Banana 2.1
Google DeepMind- Cost
- 7 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Nano Banana Lite
Google DeepMind- Cost
- 5 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, seed
Nano Banana Pro
Google DeepMind- Cost
- 15 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, negative_prompt, seed
Qwen Image 2 Edit
Alibaba- Cost
- 4 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, negative_prompt, seed
Qwen Image 2 Pro (Edit)
Alibaba- Cost
- 8 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, negative_prompt, seed
Qwen Image 3 (Edit)
Alibaba- Cost
- 8 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image, negative_prompt, seed
Qwen Image Max
Alibaba- Cost
- 8 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Reve 2.1
Reve- Cost
- 25 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Seedream 5 Flash
ByteDance- Cost
- 3 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Seedream v4.5s
ByteDance- Cost
- 4 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Seedream v5.0 Lite
ByteDance- Cost
- 4 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Seedream v5.0 Pro
ByteDance- Cost
- 7 cr.
- Inputs
- 1 img
- Outputs
- 1 img
Parameters: prompt, image
Video models (text-to-video & image-to-video)
54 modelsAnimate stills, generate motion from prompts, or chain video nodes inside a workflow. Every duration / FPS / audio combo is wired.
Bernini-R
ByteDance- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, reference_image, duration, negative_prompt, seed
Cinema Studio 4.0
Higgsfield- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, image, video_url, audio_url, duration, generate_audio, era, genre, light, pacing, camera_lens, camera_model, col
FLUX 3
Black Forest Labs- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, keyframes, video_url, mode, duration, draft, generate_audio
FLUX 3 Enhance
Black Forest Labs- Cost
- Depends on duration and resolution
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: draft_cache_url
FLUX 3 Max
Black Forest Labs- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, keyframes, duration, generate_audio, reasoning_level
Gemini Omni Flash 1.1
Google DeepMind- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, reference_video, video_url, duration
Gemini Omni Flash V1
Google DeepMind- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, reference_image, duration
Genjutsu Motion Transfer
Higgsfield- Cost
- Billed on the source video's length · from 159 cr. (5 s source, 480p)
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: video_url, image, prompt
Genjutsu Object Swap
Higgsfield- Cost
- Billed on the source video's length · from 159 cr. (5 s source, 480p)
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: video_url, image, prompt
Grok Imagine Video
xAI- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, image_url, reference_image, duration
Grok Imagine Video · Éditer
xAI- Cost
- Billed on the source video's length · from 53 cr. (source up to 8 s, 480p)
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, video_url
Grok Imagine Video · Prolonger
xAI- Cost
- Billed on the source video's length · from 141 cr. (source up to 15 s)
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, video_url, duration
Grok Imagine Video 1.5
xAI- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, image_url, reference_image, duration
Grok Imagine Video 1.5 Lite
xAI- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, image_url, duration
Happy Horse 1.0
Alibaba- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, reference_image, duration, seed
Happy Horse 1.1
Alibaba- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, reference_image, duration, seed
Kandinsky 6.0 Lite
Kandinsky Lab- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, generate_audio
Kling 4.0
Kuaishou- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, reference_video, duration
Kling 4.0 · Video Edit
Kuaishou- Cost
- Billed on the source video's length · from 57 cr. (3 s source, 720p)
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, video_url, reference_image
Kling O3 4K
Kuaishou- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, video_url, duration, generate_audio, shot_type
Kling O3 4K · Video Reference
Kuaishou- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, video_url, reference_image, keep_audio, shot_type, duration
Kling O3 Pro · Video Edit
Kuaishou- Cost
- Billed on the source video's length · from 168 cr. (source up to 10 s)
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, video_url, reference_image, keep_audio, shot_type
Kling V3
Kuaishou- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, reference_video, duration, generate_audio, negative_prompt, cfg_scale,
Kling V3 Turbo
Kuaishou- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, duration
LTX 2.3 Reframe
Lightricks- Cost
- Billed on the source video's length · from 100 cr. (source up to 10 s, 720p)
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: video_url
LTX 2.3 Video Fast
Lightricks- Cost
- Depends on duration and resolution
- Inputs
- 1–2 img
- Outputs
- Vidéo
Parameters: prompt, image_url, end_image_url, duration, fps, generate_audio
LTX 2.3 Video Pro
Lightricks- Cost
- Depends on duration and resolution
- Inputs
- 1–2 img
- Outputs
- Vidéo
Parameters: prompt, image_url, end_image_url, duration, fps, generate_audio
LTX 2.5 Fast
Lightricks- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, audio, duration, fps, generate_audio, camera_motion, guidance_scale
LTX 2.5 Pro
Lightricks- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, audio, duration, fps, generate_audio, camera_motion, guidance_scale
Luma Ray 3.2
Luma AI- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, duration
MiniMax H3 — Image to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, duration, seed, prompt_expansion_mode
MiniMax H3 — Reference to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, reference_image, reference_video, reference_audio, duration, seed, prompt_expansion_mode
MiniMax H3 — Text to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, duration, seed, prompt_expansion_mode
MiniMax H3 Max — Extend Video
MiniMax- Cost
- Billed on the source video's length · from 67 cr. (5 s source, 480P)
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, video_url, duration, output, enable_prompt_expansion, seed
MiniMax H3 Max — Image to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, duration, seed, prompt_expansion_mode
MiniMax H3 Max — Insert Video
MiniMax- Cost
- Billed on the source video's length · from 87 cr. (5 s source, 480p)
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, video_url, reference_image, reference_video, start_time, resume_time, duration, enable_prompt_expansion, color_m
MiniMax H3 Max — Multi Angle
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, camera_trajectory, duration, seed, prompt_expansion_mode
MiniMax H3 Max — Reference to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, reference_image, reference_video, reference_audio, duration, seed, prompt_expansion_mode
MiniMax H3 Max — Styles
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, style, damage_level, duration, seed
MiniMax H3 Max — Text to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, duration, seed, prompt_expansion_mode
MiniMax H3 Max Turbo — Extend Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, video_url, duration, output, enable_prompt_expansion, seed
MiniMax H3 Max Turbo — Image to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, duration, seed, prompt_expansion_mode
MiniMax H3 Max Turbo — Text to Video
MiniMax- Cost
- Depends on duration and resolution
- Inputs
- 0 img
- Outputs
- Vidéo
Parameters: prompt, duration, seed, prompt_expansion_mode
PixVerse C1
PixVerse- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, duration, generate_audio, seed
Seedance 1.5 Pro
ByteDance- Cost
- Depends on duration and resolution
- Inputs
- 1–2 img
- Outputs
- Vidéo
Parameters: prompt, image_url, end_image_url, duration, camera_fixed, seed, enable_safety_checker, generate_audio
Seedance 2 Reference to Video
ByteDance- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, image, video_url, audio_url, duration, generate_audio, seed
Seedance 2.0 Fast
ByteDance- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, video_url, audio_url, duration, generate_audio, seed
Seedance 2.0 Mini
ByteDance- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, video_url, audio_url, duration, generate_audio, seed
Seedance 2.5
ByteDance- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, video_url, audio_url, duration, generate_audio, bitrate_mode, output_fo
Vidu Q4
ShengShu- Cost
- Depends on duration and resolution
- Inputs
- 1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, duration
Wan 2.6 Flash
Alibaba- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, image_url, negative_prompt, audio_url, duration
Wan 2.7
Alibaba- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, video, audio, mode, video_usage, duration, negative_prompt, enable_prompt_expansion, ena
Wan 3.0
Alibaba- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, reference_video, reference_audio, duration, audio, seed
Wan 3.0 Prime
Alibaba- Cost
- Depends on duration and resolution
- Inputs
- 0–1 img
- Outputs
- Vidéo
Parameters: prompt, start_image, end_image, reference_image, reference_video, reference_audio, duration, audio, seed
Vector & SVG models
3 modelsGenerate native SVG output for design systems, logos and editable vector assets — no raster trace needed.
Recraft V4 Vector
Recraft- Cost
- 8 cr.
- Inputs
- 0 img
- Outputs
- 1 SVG
Parameters: prompt, colors, background_color
Recraft V4.1 Pro Vector
Recraft- Cost
- 30 cr.
- Inputs
- 0 img
- Outputs
- 1 SVG
Parameters: prompt, colors, background_color
Recraft V4.1 Vector
Recraft- Cost
- 8 cr.
- Inputs
- 0 img
- Outputs
- 1 SVG
Parameters: prompt, colors, background_color
Stop juggling subscriptions. Run every frontier model from one canvas.
One Beemm Vision plan (Starter, Studio or Scale) replaces the bill from OpenAI, Google, Black Forest Labs, Ideogram, Kling, ByteDance, xAI, Alibaba, Tencent and more. Same shared credit balance across image, video and edit models.
Catalog last updated: October 24, 2026
Keep reading
- What each model costs in creditsOne credit balance across every model — no per-provider API bill.
- Beemm Vision vs MidjourneyWhy one canvas beats a single-model subscription.
- Model ownership and training dataWho owns the outputs, and what we never train on.
- Drive these models from Claude or CursorThe MCP server: your agent reads the catalogue, plans, and generates.
- How to compare models on your own briefOne brief, three models, the renders side by side.
- Which AI video model to pickKling, Seedance, Wan, MiniMax H3, Grok and FLUX 3 compared: length, 4K, sound.