Partner Node Pricing

The following table lists the pricing of the current Partner Nodes. All prices are in credits. Partner Nodes are billed per call in credits. Comfy API GPU time and Comfy Cloud plans are priced elsewhere, on the pages linked below.

Comfy API GPU pricing

GPU time and network storage rates for a managed Comfy API deployment.

Comfy Cloud plans

Subscription plans and what each plan includes.

Comfy Router pricing

Comfy Router prices are different from Partner Node prices. See the Comfy Router pricing page for the full list.

Anthropic

Chat

Model	Input credits / 1K	5m Cache Write credits / 1K	1h Cache Write credits / 1K	Cache Hit credits / 1K	Output credits / 1K
Opus 5.5	1.207	1.509	2.414	0.121	6.035
Opus 5, Opus 4.8	1.509	1.886	3.017	0.151	7.543
Fable 5.1, Fable 5	3.017	3.772	6.035	0.302	15.087
Sonnet 5.5, Sonnet 5	0.603	0.754	1.207	0.060	3.017

Optional images add tokens billed at the same model input rates.

Beeble

Video: SwitchX Video Edit

max_resolution	Credits
720p	30.17 / 30 frames
1080p	90.52 / 30 frames

Image: SwitchX Image Edit

max_resolution	Credits
720p	30.17 / run
1080p	90.52 / run

BFL

Image

Node	Credits
Flux 1.1 [pro] Ultra Image	12.66 / run
Flux.1 Kontext [pro] Image	8.44 / run
Flux.1 Kontext [max] Image	16.88 / run
Flux.1 Expand Image	10.55 / run
Flux.1 Fill Image	10.55 / run
Flux Erase Image	6.33 / run + 0.84 / extra MP
Flux Virtual Try-On	7.91 / run + 1.06 / extra MP
FLUX.2 [pro]	6.33 / run + 3.17 / extra MP
FLUX.2 [max]	14.77 / run + 6.33 / extra MP

Image: FLUX 3 Image

Total credits = credits / image at the selected resolution.

Node	resolution	Credits / image
FLUX 3 Image	0.75K	12.37
FLUX 3 Image	1K	14.48
FLUX 3 Image	1.5K	21.12
FLUX 3 Image	2K	30.17
FLUX 3 Image	4K	183.15

Video: FLUX 3

Total credits = (credits / sec) × duration (duration is 5–20 seconds or auto).

Node	resolution	Credits / sec
Flux 3 Text to Video	720p	51.29
Flux 3 Text to Video	1080p	87.50
Flux 3 Text to Video	1440p	120.69
Flux 3 Text to Video	2160p	241.38
Flux 3 Image to Video	720p	51.29
Flux 3 Image to Video	1080p	87.50
Flux 3 Image to Video	1440p	120.69
Flux 3 Image to Video	2160p	241.38
Flux 3 Video Continuation	720p	123.71
Flux 3 Video Continuation	1080p	159.92
Flux 3 Video Continuation	1440p	196.12
Flux 3 Video Continuation	2160p	286.64

Video: FLUX 3 Max

Total credits = (credits / sec) × duration (duration is 5–20 seconds). reasoning_level and generate_audio do not change the price. Launch promo rates apply until November 7, 2026 (00:00 UTC); standard rates apply after that.

Node	resolution	Promo credits / sec	Standard credits / sec
FLUX 3 Max Text to Video	720p	12.82	51.29
FLUX 3 Max Text to Video	1080p	21.88	87.50
FLUX 3 Max Image to Video	720p	12.82	51.29
FLUX 3 Max Image to Video	1080p	21.88	87.50

Video: Flux Video Edit

Total credits = (credits / sec) × duration. Source clips of 0.7 to 15 seconds are edited from a text instruction.

Node	Credits / sec
Flux Video Edit	9.05

Video: Flux Video Upscale

Rates are per output megapixel per second. Total credits = credits / MP / sec × output megapixels × duration. target_resolution sets the output size: 1080p, 2K and 4K fit the source into that size, and by factor scales the source by upscale_factor (1.5 to 3). Output is capped at about 14.4 MP per frame.

Node	mode	Credits / MP / sec
Flux Video Upscale	creative	15.09
Flux Video Upscale	precise	10.56

A 1080p output (2.07 MP) costs 31.24 credits per second in creative mode and 21.86 in precise. A 4K output (8.29 MP) costs 125.10 and 87.54.

Bria

Image

Node	Credits
Bria Generative Fill	9.05 / run
Bria Eraser	6.03 / run
Bria Expand Image	6.03 / run
Bria Increase Resolution	6.03 / run
Bria FIBO 2.0 Image Edit	12.07 / run
Bria FIBO 2.0 Image Generate	12.07 / run
Bria Remove Image Background	3.8 / run
Bria Erase by Text	12.07 / run
Bria Add Object	12.07 / run
Bria Replace Object	12.07 / run
Bria Relight	12.07 / run
Bria Restore Photo	12.07 / run
Bria Reseason	12.07 / run
Bria Erase Foreground	12.07 / run
Bria Replace Image Background	12.07 / run
Bria Guided Remove Background	9.05 / run
Bria Product Holding	12.07 / run
Bria Virtual Try-On	12.07 / run

Video

Node	Credits
Bria Remove Video Background	10.55 / sec
Bria Video Green Screen	10.55 / sec
Bria Video Replace Background	10.55 / sec
Bria Remove Video Background (Transparent)	10.55 / sec
Bria Video Eraser	13.58 / sec

ByteDance

LLM: ByteDance Seed

Per million tokens. Rates below are for prompt length [0, 128]K; longer prompts use higher tiers.

Model	Input credits / 1M	Cache hit credits / 1M	Output credits / 1M
Seed 2.0 Pro (`seed-2-0-pro-260328`)	105.5	21.1	633
Seed 2.0 Lite (`seed-2-0-lite-260228`)	52.75	10.55	422
Seed 2.0 Mini (`seed-2-0-mini-260215`)	21.1	4.22	84.4

Optional images and videos add input tokens at the input rate.

Image: ByteDance Seedream

Per successfully generated image.

model	Credits / image
seedream 5.0 pro (`seedream-5-0-pro-260628`)	9.50 (1K) / 18.99 (2K)
seedream 5.0 flash (`seedream-5-0-flash-260915`)	5.43
seedream 5.0 lite (`seedream-5-0-260128`)	7.39
seedream-4-5-251128	8.44
seedream-4-0-250828	6.33
Seedream 5.0 Pro Layer Separation	6.79 (1K, 1.5K) / 13.58 (2K)
Seedream 5.0 Flash Layer Separation	5.43

Seedream 5.0 Pro uses resolution-based billing: 1K (≤2.61 MP, 9.50 credits) and 2K (>2.61 MP, 18.99 credits). Seedream 5.0 Flash bills a flat 5.43 credits per image at every resolution. The first image in each request is free. Each additional image beyond the first (including both output and input/reference images) adds 0.63 credits.

Image: ByteDance Image (deprecated)

Deprecated: The ByteDance Image node (Seedream 3.0) has been retired and removed from ComfyUI. The pricing below is retained for reference only.

model	Credits / image
seedream-3-0-t2i-250415	6.33

Video: Seedance 2.5

Token-based billing. Estimated token consumption = (input video duration + output video duration) × output video width × output video height × output video frame rate ÷ 1024. When input is text, image, or audio only, input video duration = 0. Actual usage from the API is authoritative.

Model	Resolution	Video input	Credits / 1K tokens
Seedance 2.5	480p, 720p	no	3.229
Seedance 2.5	480p, 720p	yes	1.931
Seedance 2.5	1080p	no	3.530
Seedance 2.5	1080p	yes	2.112

Video input means a reference video is connected. Text, image, and audio references count as no video input. Minimum token consumption limits apply when the input includes video: if the estimated consumption is below the limit, billing uses the minimum. Reference videos must be at least 2 seconds long, and total input is limited to 30 seconds. Estimated charges for 16:9 output at 24 fps:

Resolution	5s output, no video input	5s output + 2–30s video input
480p	155.1	166.9 – 649.3
720p	348.8	375.4 – 1459.8
1080p	857.8	923.9 – 3592.7

Video: Seedance 2.0

480p and 720p share the same rate. Fast and Mini do not support 1080p or 4K. Estimated token consumption:

(Input video duration + Output video duration) × Output video width × Output video height × Output video frame rate ÷ 1024

When input is text, image, or audio only, input video duration = 0. Actual usage from the API is authoritative.

Model	Resolution	Video input	Credits / 1K tokens
Seedance 2.0	480p, 720p	no	2.112
Seedance 2.0	480p, 720p	yes	1.297
Seedance 2.0	1080p	no	2.323
Seedance 2.0	1080p	yes	1.418
Seedance 2.0	4k	no	1.207
Seedance 2.0	4k	yes	0.724
Seedance 2.0 Fast	480p, 720p	no	1.690
Seedance 2.0 Fast	480p, 720p	yes	0.996
Seedance 2.0 Mini	480p, 720p	no	1.056
Seedance 2.0 Mini	480p, 720p	yes	0.634

Video input means reference video is connected. Text, image, and audio references count as no video input. For video-to-video inputs, a minimum token usage may apply. Seedance 2.0 outputs at 24fps.

Video: Seedance 1.x

Billed by tokens (same estimation formula as Seedance 2.0). Unlike Seedance 2.0, the token rate does not change by resolution; resolution changes how many tokens a clip uses (via width × height in the formula), so higher resolutions cost more. Token rate

Model	Condition	Credits / 1M tokens
seedance-1-0-pro-250528	—	527.5
seedance-1-0-pro-fast-251015	—	211

Deprecated: seedance-1-5-pro-251215 retires on November 11, 2026, when BytePlus shuts the model down. ComfyUI removes it from the ByteDance 1.x nodes on the same date, and its pricing rows are removed from this page. Use seedance-1-0-pro-250528, seedance-1-0-pro-fast-251015, or a Seedance 2.x model instead.Already retired: seedance-1-0-lite-t2v-250428 and seedance-1-0-lite-i2v-250428, and the ByteDance Reference Images to Video node, have been retired and removed from ComfyUI. Their pricing below is retained for reference only.

Approximate credits / 10 sec (scale with duration ÷ 10. Ranges reflect aspect ratio.)

model	resolution	generate_audio	Credits / 10 sec
seedance-1-0-pro-250528	480p	—	48.53 – 50.64
seedance-1-0-pro-250528	720p	—	107.61 – 118.16
seedance-1-0-pro-250528	1080p	—	248.98 – 257.42
seedance-1-0-pro-fast-251015	480p	—	18.99 – 21.1
seedance-1-0-pro-fast-251015	720p	—	44.31 – 48.53
seedance-1-0-pro-fast-251015	1080p	—	99.17 – 103.39
seedance-1-0-lite-i2v-250428	480p	—	35.87 – 37.98
seedance-1-0-lite-i2v-250428	720p	—	78.07 – 86.51
seedance-1-0-lite-i2v-250428	1080p	—	179.35 – 185.68

ByteDance Reference Images to Video (480p and 720p only):

model	resolution	Credits / 10 sec
seedance-1-0-pro-250528	480p	48.53 – 50.64
seedance-1-0-pro-250528	720p	107.61 – 118.16
seedance-1-0-lite-i2v-250428	480p	35.87 – 37.98
seedance-1-0-lite-i2v-250428	720p	78.07 – 86.51

Video: ByteDance vCube Video Enhance

Billed per second of enhanced output. The rates below are per second at 30 fps or below. Rates from 31 to 60 fps double the rate, and rates above 60 fps quadruple it. With source resolution or frame rate selected, the rate scales with the source video (approximately 1× to 4×).

tool_version	Resolution	Credits / second
standard	720p	~1.04
standard	1080p	~2.08
standard	2K	~4.16
standard	4K	~8.31
standard	8K	~33.25
professional	720p	~10.39
professional	1080p	~20.78
professional	2K	~41.56
professional	4K	~83.12
professional	8K	~332.47

Audio: ByteDance Seed Audio 1.0

Per minute of generated audio. Total credits = credits / min × duration (minutes).

Node	Credits
ByteDanceSeedAudio	~45.26 / min

Clarity AI

Image

Per megapixel of output. Total credits = (credits / MP) × output megapixels.

model	Node	Credits / MP
Crystal Upscaler	Clarity AI Crystal Upscale	4.83

Video: Crystal Video Upscale

Per megapixel of output per second. Total credits = (credits / MP / sec) × output megapixels × duration (seconds) × frame-rate factor. The factor steps every 30 fps: 1x up to 30 fps, 2x up to 60 fps, 3x up to 90 fps, and one more step for each further 30 fps. Output is capped at 9 MP.

Node	Credits / MP / sec
Clarity AI Crystal Video Upscale	30.17

At up to 30 fps, a 1080p output costs about 62.56 credits per second and the 9 MP ceiling about 271.56.

ElevenLabs

Node	Model	Credits
ElevenLabs Text to Speech	`eleven_v4`	24.14 / 1K chars
ElevenLabs Text to Speech	`eleven_v4_turbo`	12.07 / 1K chars
ElevenLabs Text to Speech	`eleven_v3`, `eleven_multilingual_v2`	50.64 / 1K chars
ElevenLabs Text to Dialogue	`eleven_v4`	24.14 / 1K chars
ElevenLabs Text to Dialogue	`eleven_v4_turbo`	12.07 / 1K chars
ElevenLabs Text to Dialogue	`eleven_v3`	50.64 / 1K chars
ElevenLabs Speech to Text	—	1.54 / min
ElevenLabs Speech to Speech	—	50.64 / min
ElevenLabs Text to Sound Effects	—	29.54 / min
ElevenLabs Voice Isolation	—	50.64 / min
ElevenLabs Instant Voice Clone	—	31.65 / run

FishAudio

Limited-time offer: from October 13 to November 12, 2026, Drama 3 is billed at about 3.02 credits per 1K bytes. The drama-3 row in the table lists the standard price, which applies again from November 13, 2026.

Node	Model	Credits
Fish Audio Text to Speech	s2.1-pro, s1	~4.53 / 1K bytes
Fish Audio Text to Speech	drama-3	~7.54 / 1K bytes
Fish Audio Speech to Text	—	~1.81 / minute
Fish Audio Instant Voice Clone	—	Free

Magnific

Image: Upscale

Magnific Image Upscale (Creative) and Magnific Image Upscale (Precise V2) share the same billing. Upscaling runs in 2x steps (2x = 1 step, 4x = 2, 8x = 3, 16x = 4). After each step, pixel count ×4; each step is priced by the input megapixels at that step.

Input MP at step	Credits / 2x step
≤1.3	35.91
≤3.0	71.82
≤6.4	107.73
>6.4	430.88

Total credits = sum of all steps for your scale_factor. Example: 4x on a 1 MP image → step 1 at 1 MP (35.91) + step 2 at 4 MP (107.73) = 143.64 credits.

Image: Edit

Node	Credits
Magnific Image Style Transfer	23.21 / run
Magnific Image Relight	23.21 / run
Magnific Image Skin Enhancer (creative)	61.19 / run
Magnific Image Skin Enhancer (faithful)	78.07 / run
Magnific Image Skin Enhancer (flexible)	94.95 / run

Google

Chat: Google Gemini

Token-based billing; thought tokens use the output text rate.

Model	Input credits / 1K	Output credits / 1K
Gemini 3.8 Flash (`gemini-3.8-flash`)	0.4526	2.263
Gemini 3.7 Flash (`gemini-3.7-flash`)	0.4526	2.263
Gemini 3.5 Flash (`gemini-3.5-flash`)	0.3165	1.899
Gemini 3.1 Pro (`gemini-3.1-pro-preview`)	0.422	2.532
Gemini 3.1 Flash-Lite (`gemini-3.1-flash-lite-preview`)	0.05275	0.3165
Gemini 2.5 Pro (`gemini-2.5-pro`)	0.26375	2.11
Gemini 2.5 Flash (`gemini-2.5-flash`)	0.0633	0.5275

Image: Nano Banana

Token-based billing.

Model	Input credits / 1K	Output (text) credits / 1K	Output (image) credits / 1K
Nano Banana (`gemini-2.5-flash-image`)	0.0633	0.5275	6.33
Nano Banana Pro (`gemini-3-pro-image`)	0.5064	3.0384	30.38
Nano Banana 2 (`gemini-3.1-flash-image`)	0.1266	0.7596	15.19
Nano Banana 2 Lite (`gemini-3.1-flash-lite-image`)	0.0633	0.3798	7.60
Nano Banana 2.1 (`gemini-nano-banana-2.1`)	0.4526	2.263	9.05

Video: Google Gemini Omni

Billed per second of generated video. Rates are approximate.

Model	Resolution	Credits / sec
Gemini Omni Flash (`gemini-omni-flash-preview`)	—	30.57
Gemini Omni Flash 1.1 (`gemini-omni-1.1-flash`)	360p	10.19
	720p	30.57
	1080p	45.87
	4k	91.76

Video: Google Veo

Total credits = (credits / sec) × duration.

Model	Resolution	generate_audio	Credits / sec
veo-3.1-lite	720p	false	6.33
veo-3.1-lite	720p	true	10.55
veo-3.1-lite	1080p	false	10.55
veo-3.1-lite	1080p	true	16.88
veo-3.1-fast-generate	720p	false	16.88
veo-3.1-fast-generate	720p	true	21.1
veo-3.1-fast-generate	1080p	false	21.1
veo-3.1-fast-generate	1080p	true	25.32
veo-3.1-fast-generate	4k	false	52.75
veo-3.1-fast-generate	4k	true	63.3
veo-3.1-generate	720p, 1080p	false	42.2
veo-3.1-generate	720p, 1080p	true	84.4
veo-3.1-generate	4k	false	84.4
veo-3.1-generate	4k	true	126.6

HappyHorse

Total credits = (credits / sec) × duration.

Model	Resolution	Credits / sec
HappyHorse 1.0	720P	29.54
HappyHorse 1.0	1080P	50.64
HappyHorse 1.1	720P	42.24
HappyHorse 1.1	1080P	54.31

HappyHorse Video Edit supports HappyHorse 1.0 only. Billed at the same rates; total credits = (credits / sec) × output duration (3–15 sec, matches the input video).

HeyGen

Prices are set per-second, per-run, or per-1K characters.

Node	Condition	Credits
HeyGen Talking Photo	N/A	15.09 / sec
HeyGen Avatar Video	Avatar III, Digital Twin	3.02 / sec
HeyGen Avatar Video	Avatar III, Photo / Studio Avatar	4.98 / sec
HeyGen Avatar Video	Avatar IV, Photo Avatar	11.62 / sec
HeyGen Avatar Video	Avatar IV, Digital Twin / Studio Avatar	24.29 / sec
HeyGen Avatar Video	Avatar V	36.21 / sec
HeyGen Avatar Video	Auto (engine chosen by the avatar look)	3.02-36.21 / sec
HeyGen Create Avatar	From prompt	301.73 / run
HeyGen Create Avatar	From photo	398.28 / run
HeyGen Video Translate	precision mode	7.54 / sec
HeyGen Video Translate	speed mode, audio only	2.87 / sec
HeyGen Video Translate	speed mode	4.07 / sec
HeyGen Text to Speech	N/A	~0.20 / sec
HeyGen Video 1.0 Reference to Video	480p, no references	3.02 / sec
HeyGen Video 1.0 Reference to Video	768p, no references	4.53 / sec
HeyGen Video 1.0 Reference to Video	2K, no references	13.58 / sec
HeyGen Video 1.0 Reference to Video	480p, with reference media	6.03 / sec
HeyGen Video 1.0 Reference to Video	768p, with reference media	9.05 / sec
HeyGen Video 1.0 Reference to Video	2K, with reference media	27.16 / sec
HeyGen Video 1.0 Image to Video	480p	3.02 / sec
HeyGen Video 1.0 Image to Video	768p	4.53 / sec
HeyGen Video 1.0 Image to Video	2K	13.58 / sec
HeyGen Voice 1.0 Instant Clone	N/A	Free
HeyGen Voice 1.0 Text to Speech	`heygen-voice-1`	9.05 / 1K chars
HeyGen Voice 1.0 Text to Speech	`heygen-voice-1-turbo`	2.26 / 1K chars

Text to speech pricing: a launch rate of about 4.53 credits per 1K characters for heygen-voice-1 and 1.21 for heygen-voice-1-turbo applied through October 31, 2026. The rows above list the standard rates, which apply from November 1, 2026. Avatar video bills per second at the rate of the selected avatar look’s type (Digital Twin, Photo Avatar, or Studio Avatar). Auto picks the engine per look, so its rate spans the full range above; a custom avatar ID is billed by its own type. HeyGen Video 1.0 clips run from 5 to 15 seconds and bill at the rate of the selected resolution. Reference to Video uses the no-reference rate until a reference image or video is connected, and each reference video adds 5 seconds to the billed duration. 2K output requires the 16:9 or 9:16 aspect ratio; auto works at 2K only when no reference media is connected.

Higgsfield

Total credits = (credits / sec) × video duration. The source video must be at least 4 seconds; only the first 30 seconds are used.

Node	model	resolution	Credits / sec
Higgsfield Genjutsu Motion Transfer	genjutsu-v1.0	480p	95.95
Higgsfield Genjutsu Motion Transfer	genjutsu-v1.0	720p	205.48
Higgsfield Genjutsu Motion Transfer	genjutsu-v1.0	1080p	492.42

Hitpaw

Video: HitPaw Video Enhance

Total credits = (credits / sec) × video duration. Rates depend on input FPS. Portrait Restore / General Restore (Portrait Restore 1x/2x, General Restore 1x/2x/4x):

Resolution	FPS	Credits / sec
720P	<30fps	2.11
720P	30–60fps	4.22
720P	60–120fps	8.44
720P	≥120fps	12.66
1080P	<30fps	3.17
1080P	30–60fps	6.33
1080P	60–120fps	12.66
1080P	≥120fps	18.99
2K	<30fps	4.22
2K	30–60fps	8.23
2K	60–120fps	16.46
2K	≥120fps	24.69
4K	<30fps	5.28
4K	30–60fps	10.76
4K	60–120fps	21.31
4K	≥120fps	32.07
8K	<30fps	6.96
8K	30–60fps	13.93
8K	60–120fps	27.85
8K	≥120fps	41.78

Ultra HD (Ultra HD Model 2x):

Resolution	FPS	Credits / sec
720P	<30fps	3.17
720P	30–60fps	6.54
720P	60–120fps	13.08
720P	≥120fps	19.41
1080P	<30fps	4.22
1080P	30–60fps	8.44
1080P	60–120fps	16.88
1080P	≥120fps	25.32
2K	<30fps	5.49
2K	30–60fps	10.97
2K	60–120fps	21.94
2K	≥120fps	32.92
4K	<30fps	7.17
4K	30–60fps	14.35
4K	60–120fps	28.49
4K	≥120fps	42.83
8K	<30fps	9.28
8K	30–60fps	18.57
8K	60–120fps	37.14
8K	≥120fps	55.7

Generative (Generative Model 1x; up to 4K):

Resolution	FPS	Credits / sec
720P	<30fps	3.17
720P	30–60fps	6.33
720P	60–120fps	12.66
720P	≥120fps	18.99
1080P	<30fps	5.28
1080P	30–60fps	10.55
1080P	60–120fps	21.1
1080P	≥120fps	31.65
2K	<30fps	8.02
2K	30–60fps	15.82
2K	60–120fps	31.65
2K	≥120fps	47.48
4K	<30fps	11.82
4K	30–60fps	23.84
4K	60–120fps	47.48
4K	≥120fps	71.32

Image: HitPaw General Image Enhance

Generative Portrait:

Megapixels	Credits / run
<8MP	4.22
8–12MP	6.33
12–24MP	8.44
24–34MP	12.66

Generative:

Megapixels	Credits / run
<8MP	10.55
8–12MP	12.66
12–24MP	16.88
24–34MP	31.65

Ideogram

Node	turbo	Character reference	rendering_speed	Credits / image
Ideogram V1	false	—	—	18.1
Ideogram V1	true	—	—	6.03
Ideogram V2	false	—	—	24.14
Ideogram V2	true	—	—	15.09
Ideogram V4	—	—	TURBO	9.05
Ideogram V4	—	—	DEFAULT	18.1
Ideogram V4	—	—	QUALITY	30.17

Node	quality	resolution	Credits / image
Ideogram & Pruna P-Image	VERY_LOW	1K	0.91
Ideogram & Pruna P-Image	VERY_LOW	2K	1.81
Ideogram & Pruna P-Image	LOW	1K	2.26
Ideogram & Pruna P-Image	LOW	2K	4.53
Ideogram & Pruna P-Image	MEDIUM	1K	3.02
Ideogram & Pruna P-Image	MEDIUM	2K	6.03
Ideogram & Pruna P-Image	HIGH	1K	4.53
Ideogram & Pruna P-Image	HIGH	2K	9.05

Node	quality	Credits / image
Ideogram 4.5 Text to Image	very_low	2.41
Ideogram 4.5 Text to Image	low	9.05
Ideogram 4.5 Text to Image	medium	18.1
Ideogram 4.5 Text to Image	high	60.35
Ideogram 4.5 Edit, Ideogram 4.5 Precise Edit	low	9.05
Ideogram 4.5 Edit, Ideogram 4.5 Precise Edit	medium	18.1
Ideogram 4.5 Edit, Ideogram 4.5 Precise Edit	high	60.35

Ideogram Vector returns an editable SVG instead of a raster image:

Node	quality	Reference images	Credits / SVG
Ideogram Vector Generate SVG	low	—	39.22
Ideogram Vector Generate SVG	medium	—	48.28
Ideogram Vector Generate SVG	high	No	60.35
Ideogram Vector Generate SVG	high	Yes	96.55
Ideogram Vector Image to SVG	—	—	30.17

Krea

Model	Style reference	Moodboard	Credits / run
Krea 2 Medium Turbo	No	No	3.17
Krea 2 Medium Turbo	Yes	No	3.69
Krea 2 Medium Turbo	—	Yes	4.22
Krea 2 Medium	No	No	6.33
Krea 2 Medium	Yes	No	7.39
Krea 2 Medium	—	Yes	8.44
Krea 2 Large	No	No	12.66
Krea 2 Large	Yes	No	13.72
Krea 2 Large	—	Yes	14.77

Image: Krea 3

Total credits = credits / image at the selected resolution and thinking_mode, plus a per-reference-image surcharge when images are connected.

Model	Resolution	Thinking mode	Credits / image	Per reference image
Krea 3	1K	fast	9.05	6.03
Krea 3	1K	high	15.09	6.03
Krea 3	2K	fast	18.10	6.03 - 21.12
Krea 3	2K	high	24.14	6.03 - 21.12
Krea 3	2K	ultra	78.45	6.03 - 21.12

At 2K, each reference image adds 6.03 to 21.12 credits, depending on the reference image’s pixel size; at 1K reference images are downscaled to about 1 MP, so the surcharge is a flat 6.03 credits. ultra always outputs 2K regardless of resolution and requires at least one reference image.

Kling

Video: Credits / sec

Total credits = (credits / sec) × duration, except Kling 3.0 Omni Edit Video and Kling Motion Control (billed per second of output; duration follows input video on Edit).

kling-video-o1

task	resolution	Credits / sec
generation	720p	17.72
generation	1080p	23.63
video to video, edit	720p	26.59
video to video, edit	1080p	35.45

kling-v3-omni

task	resolution	generate_audio	Credits / sec
generation	720p	false	17.72
generation	720p	true	23.63
generation	1080p	false	23.63
generation	1080p	true	29.54
generation	4k	false, true	88.62
video to video, edit	720p	—	26.59
video to video, edit	1080p	—	35.45

kling-3.0-turbo

Always generates audio; the audio toggle is ignored.

resolution	Credits / sec
720p	23.63
1080p	29.54

kling-v3

task	resolution	generate_audio	Credits / sec
generation	720p	false	17.72
generation	720p	true	26.59
generation	1080p	false	23.63
generation	1080p	true	35.45
generation	4k	false, true	88.62

task	mode	Credits / sec
motion control	std	26.59
motion control	pro	35.45

kling-v2-6

task	generate_audio	mode	Credits / sec
generation	false	—	14.77
generation	true	—	29.54
motion control	—	std	14.77
motion control	—	pro	23.63

End of life (EOL): Kling V1.5, V1.6, V2.1, V2.1 Master, and Kolors Virtual Try-On are scheduled for retirement on September 15, 2026. The pricing below is retained for reference until removal.

kling-v2-5-turbo

Kling Text to Video, Kling Image (First Frame) to Video, and Kling Start-End Frame to Video use kling-v2-5-turbo in pro mode only, billed per run at a fixed 5s or 10s duration.

Node	mode	Credits / run
Kling Text to Video	pro	73.85 (5s), 147.7 (10s)
Kling Image (First Frame) to Video	pro	73.85 (5s), 147.7 (10s)
Kling Start-End Frame to Video	pro	73.85 (5s), 147.7 (10s)

Kling Avatar 2.0

mode	Credits / sec
std	11.82
pro	23.63

Video: Credits / run

Model	task	Credits / run
—	Lip Sync	14.77

Deprecated: The Kling Video Extend node has been retired and removed from ComfyUI.

Image

Model	resolution	Image input	Credits
kling-image-o1	1K, 2K	—	5.91 / image
kling-image-o1	4K	—	11.82 / image
kling-v3-omni	1K, 2K	—	5.91 / image
kling-v3-omni	4K	—	11.82 / image
kling-v3	—	No	5.91 / image

Total image credits = (credits / image) × n on Kling 3.0 Image; multiply by series_amount on Kling 3.0 Omni Image (kling-image-o1 always ×1).

Image: Virtual Try-On

Per run.

Node	Credits / run
Kling Virtual Try-On	33.79

Lightricks

Video: Credits / sec

Total credits = (credits / sec) × duration.

Deprecated: The LTXV Text To Video and LTXV Image To Video nodes (LTX-2 Pro / LTX-2 Fast) have been retired and removed from ComfyUI. Use LTX-2.5 instead. The pricing below is retained for reference only.

Model	resolution	Credits
LTX-2.5 (Pro)	720p	36.21 / sec
LTX-2.5 (Pro)	1080p	51.29 / sec
LTX-2.5 (Fast)	720p	27.16 / sec
LTX-2.5 (Fast)	1080p	39.22 / sec
LTX-2.5 (Fast)	1440p	57.33 / sec
LTX-2.5 (Fast)	4K	90.52 / sec
LTX-2.5 Audio To Video (Pro)	—	51.29 / sec
LTX-2.5 Audio To Video (Fast)	—	39.22 / sec
LTX-2 (Pro)	1080p	12.66 / sec
LTX-2 (Pro)	1440p	25.32 / sec
LTX-2 (Pro)	4K	50.64 / sec
LTX-2 (Fast)	1080p	8.44 / sec
LTX-2 (Fast)	1440p	16.88 / sec
LTX-2 (Fast)	4K	33.76 / sec

Resolution maps to 1280x720 / 720x1280 (720p), 1920x1080 / 1080x1920 (1080p), 2560x1440 / 1440x2560 (1440p), and 3840x2160 / 2160x3840 (4K). Durations over 10s on LTX-2.5 (Fast) require a 720p or 1080p resolution and 24/25 FPS; on LTX-2 (Fast) they require 1080p and 25 FPS.

Luma

Video

Deprecated: The legacy Luma Text to Video and Luma Image to Video nodes are deprecated, and Luma removed the endpoints they use on October 24, 2026, so these two nodes can no longer generate videos. Use the Luma Ray 3.2 nodes instead. The ray-2, ray-flash-2, and ray-1-6 rows below are retained for reference only; ray-1-6 stopped being served in September 2026.

Flat /run prices match the node badge for each duration choice. Edit and reframe bill (credits / sec) × video length. ray-1-6 is always 105.50 / run.

Model	task	resolution	Credits
ray-3.2	generation	360p	12.66 / run (5s), 37.98 / run (10s)
ray-3.2	generation	540p	31.65 / run (5s), 94.95 / run (10s)
ray-3.2	generation	720p	63.30 / run (5s), 189.90 / run (10s)
ray-3.2	generation	1080p	253.20 / run (5s), 759.60 / run (10s)
ray-3.2	edit	360p	22.79 / sec
ray-3.2	edit	540p	30.38 / sec
ray-3.2	edit	720p	45.58 / sec
ray-3.2	edit	1080p	91.15 / sec
ray-3.2	reframe	360p	6.33 / sec
ray-3.2	reframe	540p	12.66 / sec
ray-3.2	reframe	720p	25.32 / sec
ray-3.2	reframe	1080p	75.96 / sec
ray-2	generation	540p	120.27 / run (5s), 217.33 / run (9s)
ray-2	generation	720p	215.22 / run (5s), 386.13 / run (9s)
ray-2	generation	1080p	478.97 / run (5s), 865.10 / run (9s)
ray-2	generation	4K	1922.21 / run (5s), 3460.40 / run (9s)
ray-flash-2	generation	540p	42.20 / run (5s), 75.96 / run (9s)
ray-flash-2	generation	720p	71.74 / run (5s), 128.71 / run (9s)
ray-flash-2	generation	1080p	166.69 / run (5s), 299.62 / run (9s)
ray-flash-2	generation	4K	660.43 / run (5s), 1192.15 / run (9s)
ray-1-6	generation	—	105.50 / run

Luma Ray 3.2 Image to Video and Extend Video always bill the 5s price. Legacy Image to Video uses 5s or 9s from ray-2 / ray-flash-2 rows.

Image

Model	task	Credits
photon-flash-1	—	0.57 / run
photon-1	—	2.19 / run
uni-1	generation	8.52 / run + 0.63 / ref image (≤ 9)
uni-1	edit	9.16 / run + 0.63 / ref image (≤ 8)
uni-1-max	generation	21.10 / run + 0.63 / ref image (≤ 9)
uni-1-max	edit	21.73 / run + 0.63 / ref image (≤ 8)

Reference-image surcharge uses USD rounded to 4 decimals before converting to credits.

Meshy

Node	Options	Credits
Meshy: Text to Model	—	241.4 / run
Meshy: Refine Draft Model	2K, 4K texture	120.7 / run
Meshy: Refine Draft Model	8K texture	181.0 / run
Meshy: Image to Model	No texture	241.4 / run
Meshy: Image to Model	Texture (2K, 4K)	362.1 / run
Meshy: Image to Model	Texture (8K)	422.4 / run
Meshy: Multi-Image to Model	No texture	241.4 / run
Meshy: Multi-Image to Model	Texture (2K, 4K)	362.1 / run
Meshy: Multi-Image to Model	Texture (8K)	422.4 / run
Meshy: Rig Model	—	60.35 / run
Meshy: Animate Model	—	36.21 / run
Meshy: Texture Model	2K, 4K texture	120.7 / run
Meshy: Texture Model	8K texture	181.0 / run
Meshy: Texture Multi-View	2K, 4K texture	120.7 / run
Meshy: Texture Multi-View	8K texture	181.0 / run
Meshy: Text to Model (Smart Topology)	—	60.35 / run
Meshy: Image to Model (Smart Topology)	No texture	60.35 / run
Meshy: Image to Model (Smart Topology)	Texture (2K, 4K)	181.0 / run
Meshy: Image to Model (Smart Topology)	Texture (8K)	241.4 / run

Ultra Mode (available on Meshy 7.1, Meshy 7, and latest models) adds 60.3 credits: Text to Model 301.7 / run, Image to Model 422.4 / run (2K, 4K texture) or 482.7 / run (8K texture), Multi-Image to Model 422.4 / run (2K, 4K texture) or 482.7 / run (8K texture). The ultra pass resolution (2k, or 4k on Meshy 7.1 and latest) does not change the price. Meshy: Text to Model creates a draft mesh; run Meshy: Refine Draft Model on the returned meshy_task_id to texture it. Meshy: Image to Model and Meshy: Multi-Image to Model can texture in one step when should_texture is enabled.

Mirelo

Node	Credits / sec
Mirelo Video to SFX	2.796
Mirelo Text to SFX	2.796

Total credits = (credits / sec) × seconds billed. Mirelo Video to SFX bills the length of the input video (1 to 600 seconds). Mirelo Text to SFX bills the duration value (0.1 to 600 seconds).

Minimax

Node	model	resolution	Credits
MiniMax Text to Video	T2V-01, T2V-01-Director	—	90.73 / run
MiniMax Image to Video	I2V-01, I2V-01-Director, I2V-01-live	—	90.73 / run
MiniMax Hailuo 02 Video	MiniMax-Hailuo-02	768P	59.08 / run (6s), 118.16 / run (10s)
MiniMax Hailuo 02 Video	MiniMax-Hailuo-02	1080P	103.39 / run (6s)
MiniMax H3 Text to Video	MiniMax H3	768P	27.16 / sec
MiniMax H3 Text to Video	MiniMax H3	2K	39.22 / sec
MiniMax H3 First-Last-Frame to Video	MiniMax H3	768P	27.16 / sec
MiniMax H3 First-Last-Frame to Video	MiniMax H3	2K	39.22 / sec
MiniMax H3 Reference to Video	MiniMax H3	768P	27.16 / sec, plus 12.07 / image over 5
MiniMax H3 Reference to Video	MiniMax H3	2K	39.22 / sec, plus 12.07 / image over 5
MiniMax H3 Context IR	MiniMax H3	—	4.22 / run (text only), 10.55 / run (with first/last frame), 12.66–23.21 / run (with reference media)
MiniMax H3 Regenerate to 2K	MiniMax H3	—	15.09 / sec
MiniMax H3 Text to Video	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Text to Video	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 First-Last-Frame to Video	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 First-Last-Frame to Video	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 Reference to Video	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Reference to Video	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 Max Recast	MiniMax H3 Max	768P	90.52 / sec
MiniMax H3 Max Recast	MiniMax H3 Max	1080P	135.78 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max	1080P	48.28 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max	2K	96.55 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max Turbo	480P	7.54 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max Turbo	768P	12.07 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max Turbo	1080P	24.14 / sec
MiniMax H3 Max Extend Video	MiniMax H3 Max Turbo	2K	48.28 / sec
MiniMax H3 Max Reframe Video	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Max Reframe Video	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 Max Reframe Video	MiniMax H3 Max	1080P	48.28 / sec
MiniMax H3 Max Insert Video	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Max Insert Video	MiniMax H3 Max	768P	18.10 / sec
MiniMax H3 Max Lip Sync	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Max Lip Sync	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 Max Lip Sync	MiniMax H3 Max	1080P	48.28 / sec
MiniMax H3 Max Lip Sync	MiniMax H3 Max	2K	96.55 / sec
MiniMax H3 Max Camera Control	MiniMax H3 Max	480P	15.09 / sec
MiniMax H3 Max Camera Control	MiniMax H3 Max	768P	24.14 / sec
MiniMax H3 Max Camera Control	MiniMax H3 Max	1080P	48.28 / sec

MiniMax Hailuo 02 Video only supports 6s at 1080P. MiniMax H3 bills per second (4–15s duration). MiniMax H3 Reference to Video adds 12.07 credits per reference image beyond 5, and bills reference videos at 27.16 credits/sec (768P) or 39.22 credits/sec (2K) (2s per video, up to 15s total, approximate). MiniMax H3 Context IR prices depend on attached media: text only, first/last frame, or reference media (approximate). MiniMax H3 Max bills per second at the rates above. Text to Video, First-Last-Frame to Video, and Reference to Video use 5–15s output duration. Lip Sync accepts audio from 5 to ~899 seconds; when output exceeds 15 seconds, the 1.2× multiplier below applies. MiniMax H3 Max Reference to Video billing has two parts: the output video is billed per second at the rates above, and reference inputs are billed as tokens. Tokens from every image, video, and audio clip in the request are pooled and share one free allowance:

Reference charge (credits) = max(0, total reference tokens - 4,096) × 6.03 / 1,000

The first 4,096 tokens per request are free; beyond that, each 1K tokens costs 6.03 credits.

Reference input	Tokens
Image	(width × height) / 1024
Reference video at 480P output	2,886 / sec
Reference video at 768P output	7,459 / sec
Audio	80 / sec

A reference video is tokenized at the output resolution, not at the source clip’s resolution: for a given output resolution, a 480P and a 768P clip of the same length cost the same. Images and audio are resolution-independent. Worked examples, each assuming no other reference input consumes the free allowance:

A 1024 × 1024 image is 1,024 tokens: the first 4 images are free, then 6.03 credits each.
A 2048 × 2048 image is 4,096 tokens: the first image is free, then 24.14 credits each.
Generating a 5 s 768P video conditioned on two 1024 × 1024 images and one 5 s reference video: output 24.14 × 5 = 120.7 credits; reference tokens 2 × 1,024 + 37,296 = 39,344, minus the 4,096 allowance = 35,248 billable → 35.248 × 6.03 ≈ 212.6 credits. Total ≈ 333.3 credits.

MiniMax H3 Max Recast, Extend Video, Reframe Video, Insert Video, Lip Sync and Camera Control bill per second of video. Extend Video also runs on the Turbo model at half the Max rate. Reframe Video is billed at the table rate per second. Longer sources use overlapping windows, so billed seconds can exceed the final output duration. Lip Sync is billed at the table rate per second. When the output is over 15 seconds, a 1.2× multiplier applies (for example, 768P → 28.97 / sec). Insert Video adds reference tokens beyond the free 4,096-token allowance at 6.03 credits per 1K tokens, the same allowance as Reference to Video: 240 base tokens, 2,048 per image and 225,000 per reference video at 768P output (87,000 at 480P).

OpenAI

DALL·E and Sora use fixed per-image or per-second rates. OpenAI GPT Image 2 and OpenAI ChatGPT bill from API token usage.

Image: DALL·E

Deprecated: The OpenAI DALL·E 2 and OpenAI DALL·E 3 nodes have been retired and removed from ComfyUI. Use GPT Image instead. The pricing below is retained for reference only.

DALL·E 2 supports 256×256, 512×512, or 1024×1024; total credits = (credits / image) × n. DALL·E 3 adds quality (standard / hd) and supports 1024×1024 or portrait 1024×1792 / 1792×1024.

Node	quality	size	Credits
OpenAI DALL·E 2	—	256x256	3.38 / image
	—	512x512	3.80 / image
	—	1024x1024	4.22 / image
OpenAI DALL·E 3	standard	1024x1024	8.44 / run
	standard	1024x1792, 1792x1024	16.88 / run
	hd	1024x1024	16.88 / run
	hd	1024x1792, 1792x1024	25.32 / run

Image: GPT Image

Billed from API token usage after generation. Approximate badge by quality (low / medium / high); actual cost follows token counts below.

model	token type	Credits / 1M
gpt-image-1	input	2110
gpt-image-1	output (image)	8440
gpt-image-1.5	input	1688
gpt-image-1.5	output (image)	6752
gpt-image-2	input	2025.6
gpt-image-2	output (image)	7600

The deprecated OpenAI GPT Image 2 node (older implementation) uses the same models and rates. The GPT Image 2.5 models (gpt-image-2.5-flare, gpt-image-2.5-sunburst) share the same rates and add xhigh and max quality tiers.

model	token type	Credits / 1M
gpt-image-2.5-flare	input (image)	2413.84
gpt-image-2.5-flare	input (text)	1508.65
gpt-image-2.5-flare	output (image)	9051.9
gpt-image-2.5-sunburst	input (image)	2413.84
gpt-image-2.5-sunburst	input (text)	1508.65
gpt-image-2.5-sunburst	output (image)	9051.9

Output token counts scale with size and quality (for example, 1024x1024 at low is about 196 output tokens, roughly 1.86 credits). Each 1024x1024 reference image adds about 2.47 credits of image input, and prompt text is billed at the text-input rate. Multiplying images (n) scales the total.

Chat

Token-based billing. Badge rates are per 1K tokens; table is per 1M tokens.

Model	Input credits / 1M	Output credits / 1M
gpt-6-astra	3017.3	15086.5
gpt-6-sol	603.46	3017.3
gpt-6-luna	30.17	150.87
gpt-5.6-sol, gpt-5.6-sol-pro	1055	6330
gpt-5.6-terra, gpt-5.6-terra-pro	527.5	3165
gpt-5.6-luna, gpt-5.6-luna-pro	211	1266
gpt-5.5	1055	6330
gpt-5.5-pro	6330	37980
gpt-5	263.75	2110
gpt-5-mini	52.75	422
gpt-5-nano	10.55	84.4
gpt-4.1	422	1688
gpt-4.1-mini	84.4	337.6
gpt-4.1-nano	21.1	84.4
o3	2110	8440
o4-mini	232.1	928.4
o1	3165	12660
o1-pro	31650	126600

Optional images and files add input tokens at the same model rates.

Video: Sora

Deprecated: The OpenAI Sora - Video node has been retired and removed from ComfyUI. The pricing below is retained for reference only.

Total credits = (credits / sec) × duration (duration is 4, 8, or 12).

model	size	Credits
sora-2	720x1280, 1280x720	21.10 / sec
sora-2-pro	720x1280, 1280x720	63.30 / sec
sora-2-pro	1024x1792, 1792x1024	105.50 / sec

sora-2 only supports 720x1280 and 1280x720.

OpenRouter

Badge rates are per 1K tokens; table is per 1M tokens. Final charges follow API usage.

Chat: OpenRouter LLM

Model	Input credits / 1M	Output credits / 1M
anthropic/claude-opus-5	1508.65	7543.25
anthropic/claude-opus-4.8	1508.65	7543.25
anthropic/claude-opus-4.7	1508.65	7543.25
anthropic/claude-fable-5	3017.30	15086.50
anthropic/claude-sonnet-5	603.46	3017.30
anthropic/claude-haiku-4.5	301.73	1508.65
openai/gpt-5.6-sol-pro	1508.65	9051.90
openai/gpt-5.6-sol	1508.65	9051.90
openai/gpt-5.6-terra-pro	754.33	4525.95
openai/gpt-5.6-terra	754.33	4525.95
openai/gpt-5.6-luna-pro	301.73	1810.38
openai/gpt-5.6-luna	301.73	1810.38
openai/gpt-5.5-pro	9051.90	54331.40
openai/gpt-5.5	1508.65	9051.90
google/gemini-3.5-flash	452.60	2715.57
x-ai/grok-4.5	603.46	1810.38
x-ai/grok-4.20	377.16	754.33
x-ai/grok-4.3	377.16	754.33
deepseek/deepseek-v4-pro	131.25	262.51
deepseek/deepseek-v4-flash	33.79	67.59
deepseek/deepseek-v3.2	76.04	114.05
qwen/qwen3.6-max-preview	313.80	1882.80
qwen/qwen3.6-plus	98.06	588.37
qwen/qwen3.6-flash	56.57	339.45
mistralai/mistral-large-2512	150.87	452.60
mistralai/mistral-medium-3-5	452.60	2262.98
z-ai/glm-4.6	129.74	525.00
z-ai/glm-5	181.04	579.32
moonshotai/kimi-k3	905.19	4525.95
moonshotai/kimi-k2.6	220.26	1053.04
moonshotai/kimi-k2-thinking	181.04	754.33
perplexity/sonar-pro	905.19	4525.95
perplexity/sonar-reasoning-pro	603.46	2413.84
perplexity/sonar-deep-research	603.46	2413.84

Image: OpenRouter Image

Token-based billing. The badge estimates cost from the prompt length, reference count, and output size; the table lists the per-1M-token credit rates used by that estimate.

Model	Prompt credits / 1M	Reference image credits / 1M	Output image credits / 1M
microsoft/mai-image-2.6	1508.65	2413.84	11465.70
microsoft/mai-image-2.6-flash	528.03	754.33	5732.87

Image notes

mai-image-2.6 and mai-image-2.6-flash bill from API token usage: the prompt, each reference image, and the generated image are tokenized, then charged at the rates above.
Reference images are downscaled to at most 2048 x 2048 (about 4,096 tokens each) before upload.

Patina

All three nodes bill per run, and every PBR map you enable adds to the price. MP is the output size in megapixels rounded up to a whole number, so every image_size preset counts as 1 MP and a custom size counts 1 to 4 MP.

Node	Credits
Patina PBR Material Maps	3.02 / run + 3.02 to 12.07 / map
Patina Material	3.02 / run + 6.03 / MP + 3.02 / MP / map
Patina Material Extract	30.17 / run + 6.03 / MP + 3.02 / MP / map

upscale_factor 2× adds 1.21 / MP / map and 4× adds 4.83 / MP / map. Patina PBR Material Maps needs at least one map enabled. Prices are approximate. A 1 MP material with the default basecolor and normal maps costs 15.09 credits, and a 4 MP output with all five maps at 4× upscale costs 184.06 credits for Patina Material or 211.21 credits for Patina Material Extract.

Pixverse

Model v3.5 (fixed in the API; not selectable). 1080p is limited to 5s with normal motion. 8s clips only support normal motion (fast is coerced to normal).

model	duration	motion_mode	quality	Credits
v3.5	5s	fast	360p, 540p	189.9 / run
	5s	fast	720p	253.2 / run
	5s	normal	360p, 540p	94.95 / run
	5s	normal	720p	126.6 / run
	5s	normal	1080p	253.2 / run
	8s	normal	360p, 540p	189.9 / run
	8s	normal	720p	253.2 / run

PixVerse V6

PixVerse V6 nodes generate videos from 1 to 15 seconds with optional native audio. Total credits = (credits / sec) × duration. PixVerse V6 Max is a second model option in the Text to Video and Image to Video nodes.

model	quality	Audio off	Audio on
PixVerse V6	360p	5.13	7.18
PixVerse V6	540p	7.18	9.23
PixVerse V6	720p	9.23	12.31
PixVerse V6	1080p	18.47	23.60
PixVerse V6 Max	360p	6.71	9.39
PixVerse V6 Max	540p	9.39	12.07
PixVerse V6 Max	720p	12.07	16.09
PixVerse V6 Max	1080p	24.14	30.84

PixVerse V6 Max runs at the rates above as an introductory price. From November 3, 2026 the per-second rates are:

quality	Audio off	Audio on
360p	8.05	12.07
540p	12.07	14.75
720p	14.75	20.12
1080p	29.50	37.55

PixVerse V6 Fusion bills 2x the per-second rate for each second of reference video, instead of the output duration. Fusion runs on PixVerse V6 rates only.

Quiver

Image

The retired arrow-1.1 models charged a fixed amount per run:

Deprecated: Quiver retired the Arrow 1-series models on October 16, 2026, and the Text to SVG and Image to SVG nodes no longer list arrow-1.1, arrow-1.1-max, or arrow-preview. Use the Arrow 2 models instead. The pricing below is retained for reference only.

model	Node	Credits / run
arrow-1.1	Quiver Text to SVG	60.35
arrow-1.1	Quiver Image to SVG	45.26
arrow-1.1-max	Quiver Text to SVG	75.43
arrow-1.1-max	Quiver Image to SVG	60.35
arrow-preview	Quiver Text to SVG	90.52
arrow-preview	Quiver Image to SVG	90.52

arrow-2 and arrow-2-telos bill by the tokens a request consumes:

model	Input credits / 1M tokens	Output credits / 1M tokens
arrow-2	1206.92	6034.6
arrow-2-telos	1810.38	9051.9

Credits = (input tokens × input rate + output tokens × output rate) ÷ 1,000,000. Input tokens cover the prompt text and, for Image to SVG, the input image; output tokens cover the generated SVG. Both nodes bill the same rates. The node badge estimates a cost range from typical token counts; the final charge follows measured usage. reasoning_effort changes how many tokens the model spends before drawing: higher levels reason for longer, so they use more output tokens and cost more.

Qwen

Image

Per image. Output is billed per generated image; Qwen Image 3 Edit also bills 0.91 credits per input reference image (up to 3). Nodes with n bill (credits / image) × n.

model	Node	Resolution	Input credits / image	Output credits / image
qwen-image-3.0	Qwen Image 3 Text to Image	1K, 2K	—	9.05 (× `n`)
qwen-image-3.0-pro	Qwen Image 3 Text to Image	1K	—	12.07 (× `n`)
qwen-image-3.0-pro	Qwen Image 3 Text to Image	2K	—	22.63 (× `n`)
qwen-image-3.0	Qwen Image 3 Edit	1K, 2K	0.91	9.05 (× `n`)
qwen-image-3.0-pro	Qwen Image 3 Edit	1K	0.91	12.07 (× `n`)
qwen-image-3.0-pro	Qwen Image 3 Edit	2K	0.91	22.63 (× `n`)

qwen-image-3.0-pro uses resolution-based output billing: 1K (≤2.25 MP) is 12.07 credits, 2K (>2.25 MP) is 22.63 credits. With the Edit node’s “auto” or “match input” size modes, Pro output pricing shows as a range (12.07–22.63); a custom size resolves to the fixed rate for that area.

Recraft

Image

Flat per-run pricing unless noted. Nodes with n bill (credits / image) × n. v3 generation nodes send model recraftv3 in the API request (not selectable in the node). The recraftv4_styles models always require a style_id or style reference images.

model	Node	Credits
recraftv4_pro	Recraft V4 Text to Image	75.43 / image (× `n`)
recraftv4_pro	Recraft V4 Text to Vector	90.52 / image (× `n`)
recraftv4_1, recraftv4_1_utility	Recraft V4 Text to Image	10.56 / image (× `n`)
recraftv4_1_flash	Recraft V4 Text to Image	2.11 / image (× `n`)
recraftv4_1_pro, recraftv4_1_utility_pro	Recraft V4 Text to Image	63.36 / image (× `n`)
recraftv4	Recraft V4 Text to Image	12.07 / image (× `n`)
recraftv4	Recraft V4 Text to Vector	24.14 / image (× `n`)
recraftv4_1_vector, recraftv4_1_utility_vector	Recraft V4 Text to Vector	24.14 / image (× `n`)
recraftv4_1_pro_vector, recraftv4_1_utility_pro_vector	Recraft V4 Text to Vector	90.52 / image (× `n`)
recraftv4_styles	Recraft V4 Text to Image	10.56 / image (× `n`)
recraftv4_styles_pro	Recraft V4 Text to Image	30.17 / image (× `n`)
recraftv4_styles_vector	Recraft V4 Text to Vector	15.09 / image (× `n`)
recraftv4_styles_pro_vector	Recraft V4 Text to Vector	36.21 / image (× `n`)
recraftv3	Recraft Text to Image, Recraft Image to Image, Recraft Image Inpainting	12.07 / image (× `n`)
recraftv3	Recraft Text to Vector	24.14 / image (× `n`)
—	Recraft Create Style	1.51 / run
—	Recraft V4 Create Style	1.51 / run
—	Recraft Replace Background	12.07 / run
—	Recraft Vectorize Image, Recraft Remove Background	3.02 / run
—	Recraft Crisp Upscale Image	1.21 / run
—	Recraft Creative Upscale Image	75.43 / run

Reve

Deprecated: Reve’s public API wound down on August 14, 2026, and the Reve Image Create, Reve Image Edit, and Reve Image Remix nodes are deprecated. They may stop working at any time; the pricing below is retained for reference.

Image

Credits below are approximate base rates (test_time_scaling=1, upscale off). test_time_scaling > 1, upscale, and remove background can increase actual charges from the API.

model	Node	upscale	Credits
reve-create@20250915	Reve Image Create	off	7.24 / run
		2x	9.64 / run
		3x	12.47 / run
		4x	16.08 / run
reve-edit@20250915, reve-remix@20250915	Reve Image Edit, Reve Image Remix	off	12.07 / run
		2x	14.47 / run
		3x	17.28 / run
		4x	20.91 / run
reve-edit-fast@20251030	Reve Image Edit	—	2.11 / run
reve-remix-fast@20251030	Reve Image Remix	—	2.11 / run

Fast edit/remix models use a flat base rate; upscale does not change the displayed estimate.

Rodin 3D

generation	Node	mode	addon_highpack	Credits
Gen-2.5	Rodin 3D Gen-2.5 - Image to 3D, Rodin 3D Gen-2.5 - Text to 3D	Regular, Fast	off	158.25 / run
Gen-2.5		Extreme-High	off	316.5 / run
Gen-2.5		any	on	+168.8 / run
Gen-2	Rodin 3D Generate - Regular Generate, Detail Generate, Smooth Generate, Sketch Generate, Gen-2 Generate	—	—	84.4 / run

HighPack (addon_highpack) adds 168.8 credits on top of the Gen-2.5 base rate for that mode.

Runway

Video

Gen4 Turbo: 5s or 10s. Total credits = (credits / sec) × duration.

End of life (EOL): gen3a_turbo and the Runway First-Last-Frame node reached end of life on July 30, 2026. Use Gen4 Turbo for image-to-video instead.

model	Credits	Status
gen4_turbo	15.09 / sec	Active
gen3a_turbo	15.09 / sec	EOL (July 30, 2026)
aleph2	84.48 / sec	Active

Runway Aleph2 Keyframe and Runway Aleph2 Prompt Image are helper nodes with no separate charge; cost is on Runway Aleph2 Video to Video.

Image

model	Credits
gen4_image	24.14 / run

Sonilo

Text to Music: total credits = (credits / sec) × duration (1–360 seconds).

Node	Credits
Sonilo Video to Music	1.9 / sec
Sonilo Text to Music	0.5275 / sec

sync.so

Total credits = (credits / sec) × duration.

Node	Credits
sync.so Lip Sync	~40.13 / sec
sync.so Talking Image	~40.13 / sec

Tencent

Text

Badge rates are per 1K tokens; table is per 1M tokens. Optional images add input tokens at the input rate.

Model	Input credits / 1M	Output credits / 1M
hy4	251.6	754.6

Image

HY Image 3.5 Preview bills one rate per generated image. 1K and 2K output, and custom sizes up to 4.19 megapixels, cost the base rate. 4K output is rendered at 2K and then upscaled by the model, and costs more, as does a custom size above 4.19 megapixels.

model	Node	Resolution	Input credits / image	Output credits / image
hy-image-3.5-preview	Tencent HY Image: Text to Image	1K, 2K, custom ≤ 4.19 MP	—	7.24
hy-image-3.5-preview	Tencent HY Image: Text to Image	4K, custom > 4.19 MP	—	9.66
hy-image-3.5-preview	Tencent HY Image: Edit	1K, 2K, custom ≤ 4.19 MP	—	7.24
hy-image-3.5-preview	Tencent HY Image: Edit	4K, custom > 4.19 MP	—	9.66

3D: Generation

3.1 uses the same rates as 3.0 but does not support LowPoly.

model	generate_type	Credits
3.0	Geometry	63.3 / run
	Normal	105.5 / run
	LowPoly	126.6 / run

Add-ons stack on the base rate:

model	option	Credits
3.0	PBR (`pbr` on)	+42.2 / run
	Custom `face_count` (≠ 500000)	+42.2 / run
	Multiview images connected	+42.2 / run

Multiview applies only to Hunyuan3D: Image(s) to Model when image_left, image_right, or image_back is connected.

3D: Post-processing

Node	Credits
Hunyuan3D: Model to UV	42.2 / run
Hunyuan3D: Smart Topology	211 / run

Hunyuan3D: 3D Texture Edit and Hunyuan3D: 3D Part each cost 126.6 / run.

Topaz

Image

Topaz Image Enhance (current node) charges per 8 megapixels of output (approximate):

model	Credits
Reimagine	67.52 / 8MP
Bloom 2	96.55 / 8MP
Wonder 3.5	24.14 / 8MP

Topaz Image Enhance (Legacy) is deprecated. It has no fixed pre-run estimate; charge comes from the API estimate at poll time (API credits × 0.08 USD). Typical charges by input resolution:

model	input resolution	Credits
Reimagine	720p (1280×720)	13.93 / run
	1080p (1920×1080)	27.85 / run
	1440p (2560×1440)	27.85 / run
	4K (3840×2160)	69.63 / run

Video

Approximate rates shown in the node are per source frame (not per second). Total credits ≈ (credits / src frame) × input frame count. With apo-8 interpolation enabled, add ~0.14 (1080p) or ~0.28 (4K) per source frame to the upscale rate.

upscaler_model	upscaler_resolution	Credits / src frame
Starlight (Astra) Fast	FullHD (1080p)	~0.43
	4K (2160p)	~0.85
Starlight Precise 2.5	FullHD (1080p)	~0.70
	4K (2160p)	~1.54
Astra 2	FullHD (1080p)	~1.72
	4K (2160p)	~2.85
Starlight (Astra) Creative	FullHD (1080p)	~2.25
	4K (2160p)	~3.99

Upscaler Disabled with apo-8 interpolation only: the UI shows Interpolation only; charge comes from the API estimate at poll time. Topaz Video Enhance (Legacy) is deprecated. It has no fixed pre-run estimate; charge comes from the API estimate at poll time.

Tripo

Legacy generation prices are approximate. The node converts internal Tripo credits to USD at credits × 0.01.

Retired: the v1.4-20240625 model version has been removed from the Tripo node’s TripoModelVersion enum in ComfyUI v0.34.0+ and can no longer be selected. Its pricing is no longer documented; migrate existing workflows to v2.5-20250123 or v3.x. The Tripo: Refine Draft model node, which only worked with v1.4 drafts, has also been removed.Legacy: Tripo: Text to Model (Legacy), Tripo: Image to Model (Legacy), and Tripo: Texture model (Legacy) are deprecated in ComfyUI v0.35.1+. They keep their exact schemas, so saved workflows keep running, but new workflows should use the current Tripo: Text to Model, Tripo: Image to Model, and Tripo: Texture model nodes. The legacy generation prices below cover both node versions.

Generation: v2.0 / v2.5

model_version v2.5-20250123. The v2.0-20240919 version has been retired and is no longer offered in the enum. texture or pbr counts as textured. On v2.5, geometry_quality: detailed does not change the price. Tripo: Text to Model

texture	texture_quality	Credits
off	standard	21.1 / run
on	standard	42.2 / run
on	detailed	63.3 / run

Tripo: Image to Model and Tripo: Multiview to Model

texture	texture_quality	Credits
off	standard	42.2 / run
on	standard	63.3 / run
on	detailed	84.4 / run

option	Credits
`quad`	+10.55 / run

quad applies to Tripo: Text to Model and Tripo: Image to Model only. smart_low_poly adds +21.1 / run on every generation node in this section and caps face_limit at 20,000 (10,000 with quad).

Generation: v3.0 / v3.1

Same nodes with model_version v3.0-20250812 or v3.1-20260211. geometry_quality: detailed adds +42.2 / run on top of the texture rows below. Tripo: Text to Model

texture	texture_quality	geometry_quality	Credits
off	standard	standard	21.1 / run
off	standard	detailed	63.3 / run
on	standard	standard	42.2 / run
on	detailed	standard	63.3 / run
on	standard	detailed	84.4 / run
on	detailed	detailed	105.5 / run
on	extreme	standard	84.4 / run
on	extreme	detailed	126.6 / run

Tripo: Image to Model and Tripo: Multiview to Model

texture	texture_quality	geometry_quality	Credits
off	standard	standard	42.2 / run
off	standard	detailed	84.4 / run
on	standard	standard	63.3 / run
on	detailed	standard	84.4 / run
on	standard	detailed	105.5 / run
on	detailed	detailed	126.6 / run
on	extreme	standard	105.5 / run
on	extreme	detailed	147.7 / run

quad add-on (+10.55 / run) applies to Tripo: Text to Model and Tripo: Image to Model only. smart_low_poly adds +21.1 / run on every generation node in this section and caps face_limit at 20,000 (10,000 with quad).

Generation: P1

model	output_mode	texture_quality	Credits (Text)	Credits (Image / Multiview)
P1-20260311	Geometry only	—	63.3 / run	84.4 / run
	Textured	standard	84.4 / run	105.5 / run
	Textured	detailed	105.5 / run	126.6 / run

Post-processing

Node	Credits
Tripo: Texture model	21.1 / run (standard), 42.2 / run (detailed), 63.3 / run (extreme)
Tripo: Rig model	52.75 / run
Tripo: Rig Check	Free
Tripo: Retarget rigged model	21.1 / run
Tripo: Segment Model	84.4 / run
Tripo: Smart Segment	116.05 / run (from a model), 179.35 / run (from an image, includes generation)
Tripo: Complete Mesh Parts	105.5 / run
Tripo: Retopology	63.3 / run
Tripo: Convert model	10.55 / run (basic), 21.1 / run (advanced options)
Tripo: Import Model	Free

Tripo: Convert model charges 21.1 / run when quad is on, face_limit is set, texture_size ≠ 4096, texture_format ≠ JPEG, flatten_bottom or pivot_to_center_bottom is on, flatten_bottom_threshold ≠ 0, or scale_factor ≠ 1; otherwise 10.55 / run.

Multiview

Node	Credits
Tripo: Image to Multiview	21.1 / run
Tripo: Edit Multiview	10.55 / run per edited view

The v3 API versions of Tripo: Image to Multiview and Tripo: Edit Multiview bill the same rates.

Generation: P2

The P2 nodes (Tripo P2: Text to Model, Tripo P2: Image to Model, Tripo P2: Multiview to Model) share one rate by texture. Prices are approximate.

texture	Credits
none	211 / run
standard	232.1 / run
detailed	253.2 / run
extreme	274.3 / run

Pruna

Pruna P-Video-2 bills per second of generated video. Total credits = (credits / sec) × duration (duration is 1-20 seconds or auto; when audio is connected, the video follows the audio length). Prices are approximate.

Node	resolution	draft	Credits / sec
Pruna P-Video-2 Text to Video	720p	off	7.54
	720p	on	4.53
	1080p	off	15.09
	1080p	on	9.05
Pruna P-Video-2 Image to Video	720p	off	7.54
	720p	on	4.53
	1080p	off	15.09
	1080p	on	9.05

VEED

Node	Options	Credits
VEED Fabric 1.0	480p	24.14 / sec
VEED Fabric 1.0	720p	45.26 / sec
VEED Lipsync 2.0	—	21.12 / sec
VEED Remove Video Background	fast, edge refinement off	2.41 / 30 frames
VEED Remove Video Background	fast, edge refinement on	3.62 / 30 frames
VEED Remove Video Background	standard, edge refinement off	4.53 / 30 frames
VEED Remove Video Background	standard, edge refinement on	6.79 / 30 frames
VEED Remove Video Background	green screen	7.54 / 30 frames
VEED Clean Audio	—	3.77 / min
VEED Clean Audio (in Video)	—	3.77 / min
VEED Dubbing	standard	33.19 / sec
VEED Dubbing	pro	54.31 / sec

Video jobs bill the length of the input. VEED Fabric 1.0 bills the audio track (up to 300 seconds), VEED Lipsync 2.0 bills the new speech (up to 600 seconds), VEED Remove Video Background is limited to 60 seconds, VEED Dubbing bills the translated track (up to 599 seconds), and VEED Clean Audio and VEED Clean Audio (in Video) bill per minute up to 30 minutes.

Vidu

Video: Q4

Total credits = (credits / sec) × duration.

model	resolution	Credits / sec
viduq4-preview	540p	9.5
	720p	20.05
	1080p	25.32
	2K	40.09
	4K	82.29

Video: Q3

Total credits = (credits / sec) × duration.

model	resolution	Credits / sec
viduq3-turbo	720p	12.66
	1080p	16.88
viduq3-pro	720p	31.65
	1080p	33.76
	2K	42.2

2K is only on Vidu Q3 Image-to-Video Generation with viduq3-pro.

Video: Q2

Linear nodes (all except Multi-Frame): base + (credits / sec) × (duration − 1). Multi-Frame: frames × base + (credits / sec) × sum of segment durations (uses the Extension / Multi-Frame base column). Reference (viduq2): add +15.825 / run when audio is on.

model	resolution	Credits / sec after 1s	Base (1s) linear nodes	Base (1s) Extension / Multi-Frame
viduq2	720p	5.275	15.825	—
	1080p	10.55	21.1	—
viduq2-pro-fast	720p	2.11	8.44	—
	1080p	4.22	16.88	—
viduq2-pro	720p	10.55	15.825	31.65
	1080p	15.825	58.025	63.3
viduq2-turbo	1080p	10.55	36.925	42.2
	720p	5.275 (Ext/MF); 10.55 (I2V/Start-End after 2s)	—	15.825

viduq2 linear bases above are for Text-to-Video. Reference-to-Video uses the same per-second rates but base 26.375 (720p) or 79.125 (1080p). viduq2-pro-fast, viduq2-pro, and viduq2-turbo linear bases are for Image-to-Video and Start/End Frame-to-Video. viduq2-turbo at 720p on those nodes: 8.44 at 1s (I2V), 10.55 at 2s (flat on I2V; Start/End minimum duration is 2s), then +10.55 / sec after 2s. The 5.275 / sec rate applies only to Extension and Multi-Frame, not I2V or Start/End.

Video: Q1

Fixed 5s at 1080p.

model	Credits
viduq1	84.4 / run

Wan

Wan 3.0 pricing: a 30% discount applied through September 30, 2026. The prices in the table are the standard prices.

model	resolution	Credits
wan2.5-t2i-preview, wan2.5-i2i-preview	—	6.33 / run
wan2.7-t2v, wan2.7-i2v	720P	21.1 / sec
	1080P	31.65 / sec
wan2.7-i2v (continuation)	720P	21.1 / sec (range)
	1080P	31.65 / sec (range)
wan2.7-videoedit	720P	21.1 / sec (in + out)
	1080P	31.65 / sec (in + out)
wan2.7-r2v	720P	21.1 / sec (range)
	1080P	31.65 / sec (range)
wan3.0-video	480P	15.09 / sec (range)
	720P	30.17 / sec (range)
	1080P	60.35 / sec (range)
wan3.0-video-prime	480P	20.52 / sec (range)
	720P	42.24 / sec (range)
	1080P	84.48 / sec (range)
wan2.5-t2v-preview, wan2.5-i2v-preview	480p	10.55 / sec
wan2.5-t2v-preview, wan2.5-i2v-preview, wan2.6-t2v, wan2.6-i2v	720p	21.1 / sec
wan2.5-t2v-preview, wan2.5-i2v-preview, wan2.6-t2v, wan2.6-i2v	1080p	31.65 / sec
wan2.6-r2v	720p	21.1 / sec (range)
	1080p	31.65 / sec (range)

WaveSpeed

model	resolution	Credits
flashvsr	720p	2.532 / sec
	1080p	3.798 / sec
	2K	5.064 / sec
	4K	6.752 / sec
SeedVR2	—	2.11 / run
Ultimate	—	12.66 / run

xAI

Video endpoints charge for moderated content.

Image

model	resolution	task	Credits
grok-imagine-image-2.0	1K	generate	12.66 (medium) / 8.44 (low) per output image
	2K	generate	16.88 (medium) / 12.66 (low) per output image
grok-imagine-image-quality	1K	generate	10.55 / output image
	2K	generate	14.77 / output image
grok-imagine-image-pro	—	generate	14.77 / output image
grok-imagine-image	—	generate	4.22 / output image
grok-imagine-image-2.0	1K	edit	2.11 input + 12.66 (medium) / 8.44 (low) per output image
	2K	edit	2.11 input + 16.88 (medium) / 12.66 (low) per output image
grok-imagine-image-quality	1K	edit	2.11 input + 10.55 / output image
	2K	edit	2.11 input + 14.77 / output image
grok-imagine-image-pro	—	edit	2.11 input + 14.77 / output image
grok-imagine-image	—	edit	0.422–1.266 input + 4.22 / output image

Video

model	resolution	Credits
grok-imagine-video	480p	10.55 / sec output (+0.422 input image)
	720p	14.77 / sec output (+0.422 input image)
grok-imagine-video-1.5	480p	24.14 / sec output (+3.02 input image)
	720p	42.24 / sec output (+3.02 input image)
	1080p	75.43 / sec output (+3.02 input image)
grok-imagine-video-1.5-lite	480p	6.03 / sec output (+3.02 input image)
	720p	9.05 / sec output (+3.02 input image)
	1080p	42.24 / sec output (+3.02 input image)
grok-imagine-video (edit)	—	12.66 / sec (input + output video)
grok-imagine-video (reference)	480p	15.09 / sec output + 0.603 / ref image
	720p	21.12 / sec output + 0.603 / ref image
grok-imagine-video (extend)	—	6.03–45.26 input + 15.09 × extension sec output / run

Cloud GPU

gpu_type	Credits
rtx_pro_6000	0.266 / sec

Comfy API GPU pricing

Comfy Cloud plans

Comfy Router pricing

​Anthropic

​Chat

​Beeble

​Video: SwitchX Video Edit

​Image: SwitchX Image Edit

​BFL

​Image

​Image: FLUX 3 Image

​Video: FLUX 3

​Video: FLUX 3 Max

​Video: Flux Video Edit

​Video: Flux Video Upscale

​Bria

​Image

​Video

​ByteDance

​LLM: ByteDance Seed

​Image: ByteDance Seedream

​Image: ByteDance Image (deprecated)

​Video: Seedance 2.5

​Video: Seedance 2.0

​Video: Seedance 1.x

​Video: ByteDance vCube Video Enhance

​Audio: ByteDance Seed Audio 1.0

​Clarity AI

​Image

​Video: Crystal Video Upscale

​ElevenLabs

​FishAudio

​Magnific

​Image: Upscale

​Image: Edit

​Google

​Chat: Google Gemini

​Image: Nano Banana

​Video: Google Gemini Omni

​Video: Google Veo

​HappyHorse

​HeyGen

​Higgsfield

​Hitpaw

​Video: HitPaw Video Enhance

​Image: HitPaw General Image Enhance

​Ideogram

​Krea

​Image: Krea 3

​Kling

​Video: Credits / sec

​kling-video-o1

​kling-v3-omni

​kling-3.0-turbo

​kling-v3

​kling-v2-6

​kling-v2-5-turbo

​Kling Avatar 2.0

​Video: Credits / run

​Image

​Image: Virtual Try-On

​Lightricks

​Video: Credits / sec

​Luma

​Video

​Image

​Meshy

​Meta

​Mirelo

​Minimax

​OpenAI

​Image: DALL·E

​Image: GPT Image

​Chat

​Video: Sora

​OpenRouter

​Chat: OpenRouter LLM

​Image: OpenRouter Image

​Image notes

​Patina

Anthropic

Chat

Beeble

Video: SwitchX Video Edit

Image: SwitchX Image Edit

BFL

Image

Image: FLUX 3 Image

Video: FLUX 3

Video: FLUX 3 Max

Video: Flux Video Edit

Video: Flux Video Upscale

Bria

Image

Video

ByteDance

LLM: ByteDance Seed

Image: ByteDance Seedream

Image: ByteDance Image (deprecated)

Video: Seedance 2.5

Video: Seedance 2.0

Video: Seedance 1.x

Video: ByteDance vCube Video Enhance

Audio: ByteDance Seed Audio 1.0

Clarity AI

Image

Video: Crystal Video Upscale

ElevenLabs

FishAudio

Magnific

Image: Upscale

Image: Edit

Google

Chat: Google Gemini

Image: Nano Banana

Video: Google Gemini Omni

Video: Google Veo

HappyHorse

HeyGen

Higgsfield

Hitpaw

Video: HitPaw Video Enhance

Image: HitPaw General Image Enhance

Ideogram

Krea

Image: Krea 3

Kling

Video: Credits / sec

kling-video-o1

kling-v3-omni

kling-3.0-turbo

kling-v3

kling-v2-6

kling-v2-5-turbo

Kling Avatar 2.0

Video: Credits / run

Image

Image: Virtual Try-On

Lightricks

Video: Credits / sec

Luma

Video

Image

Meshy

Meta

Mirelo

Minimax

OpenAI

Image: DALL·E

Image: GPT Image

Chat

Video: Sora

OpenRouter

Chat: OpenRouter LLM

Image: OpenRouter Image

Image notes

Patina

Pixverse

PixVerse V6

Quiver