Pricing

Every job is billed as a single product, chosen by the job type and a small number of config parameters (output resolution, duration, number of input images). Prompt, seed, steps and other settings do not change the price.

Tip

Use ?price=true to read back the exact product and dollar amount charged for any job.

Models

Video models

• Gemini Omni Flash
• Grok Imagine
• HappyHorse 1.1
• Kling
• LTX 2 Pro
• LTX 2.5 Fast
• MiniMax H3
• Pruna P-Video
• Runway Gen-4
• Seedance
• Seedance 2.0
• Sora 2
• Tenstorrent Wan 2.2 Lightning
• Veo 3
• Veo 3.1 Lite
• Vidu Q3 Pro
• Wan 2.6
• Wan 2.7
• Wan 3.0

Image models

• FLUX.1
• FLUX.1 Kontext
• FLUX.2
• FLUX.2 Klein 4B
• Nano Banana
• Pruna P-Image
• Qwen Image Edit Plus
• Recraft
• SDXL
• Seedream

Video utilities

• Topaz Gigapixel
• Topaz Proteus

Image utilities

• Image Utilities

Gemini Omni Flash

Applies to the job type inference.gemini-omni-flash.txt2vid.v1.

This job type uses a fixed upstream spec: the caller sends only a prompt and the upstream model decides the output resolution and length. It is priced as a single flat product per video.

Price per video

Price
$0.50

Product codes

The product field is inference-gemini-omni-flash.

Grok Imagine

Applies to the Grok Imagine job types:

• inference.grok-imagine.txt2vid.v1
• inference.grok-imagine.img2vid.v1

Priced per second of output video. Duration is billed in whole seconds (1 to 15).

Price per video

Per second	5 seconds	10 seconds	15 seconds
$0.08	$0.40	$0.80	$1.20

Product codes

The product field follows the pattern inference-grok-imagine-duration-N, where N is the billed duration in seconds (1 to 15). For example a 10-second video bills as inference-grok-imagine-duration-10.

HappyHorse 1.1

Applies to the job type inference.happyhorse-1-1.img2vid.v1.

Priced per second of output video by resolution (720P or 1080P). duration runs from 1 to 15 seconds and is billed in whole seconds, rounded up.

Price per video

Resolution	Per second	5 seconds	10 seconds	15 seconds
720P	$0.126	$0.63	$1.26	$1.89
1080P	$0.224	$1.12	$2.24	$3.36

Product codes

The product field follows the pattern inference-happyhorse-1-1-{720p,1080p}-duration-N, where N is the billed duration in seconds (1 to 15). For example a 5-second 1080P clip bills as inference-happyhorse-1-1-1080p-duration-5.

Kling

Applies to the Kling job types inference.kling.txt2vid.v1 and inference.kling.img2vid.v1.

Priced per video by the model version, mode (std or pro, where the model offers both) and duration ("5" or "10" seconds). Aspect ratio and prompt do not change the price, and image-to-video bills the same as text-to-video. model defaults to kling-v1 and mode to std when omitted.

Price per video

Model	Mode	Resolution	5 seconds	10 seconds
kling-v1	Standard	720P	$0.15	$0.30
kling-v1	Pro	1080P	$0.55	$1.10
kling-v1-6	Standard	720P	$0.25	$0.50
kling-v1-6	Pro	1080P	$0.55	$1.10
kling-v2-master	—	1080P	$1.40	$2.80
kling-v2-1	Standard	720P	$0.28	$0.56
kling-v2-1-master	—	1080P	$1.40	$2.80

kling-v2-master, kling-v2-1 and kling-v2-1-master bill the same regardless of mode.

Product codes

The product field follows the pattern inference-kling-{v1,v1-6}-{std,pro}-duration-N, inference-kling-v2-1-standard-duration-N, or inference-kling-{v2-master,v2-1-master}-duration-N, where N is 5 or 10. For example a 10-second kling-v1-6 video in pro mode bills as inference-kling-v1-6-pro-duration-10.

LTX 2 Pro

Applies to the LTX 2 Pro job types:

• inference.ltx-2-pro.txt2vid.v1
• inference.ltx-2-pro.img2vid.v1

Priced per second of output video by output resolution tier. duration runs from 1 to 10 seconds (default 8) and is billed in whole seconds, rounded up. Output resolutions above roughly 11 MP bill at the 1440p tier and above roughly 6 MP at the 4k tier; everything else bills at 720p or 1080p by output size.

Price per video

Resolution	Per second	5 seconds	8 seconds	10 seconds
720p	$0.12	$0.60	$0.96	$1.20
1080p	$0.17	$0.85	$1.36	$1.70
1440p	$0.25	$1.25	$2.00	$2.50
4k	$0.32	$1.60	$2.56	$3.20

Product codes

The product field follows the pattern inference-ltx-2-pro-{720p,1080p,1440p,4k}-duration-N, where N is the billed duration in seconds (1 to 10). For example an 8-second 1080p clip bills as inference-ltx-2-pro-1080p-duration-8.

LTX 2.5 Fast

Applies to the LTX 2.5 fast tier job types:

• inference.ltx-2.5.fast.txt2vid.v0
• inference.ltx-2.5.fast.img2vid.v0

Priced per clip by output duration. Fractional durations round up to the next whole second. Output resolution, aspect ratio and seed do not change the price, and image-to-video bills the same as text-to-video.

Price per clip

Duration	Price
1 s	$0.0152
2 s	$0.0181
3 s	$0.0231
4 s	$0.0316
5 s	$0.0346
6 s	$0.0391
7 s	$0.0445
8 s	$0.0506
9 s	$0.0581
10 s	$0.0655

Product codes

The product field follows the pattern inference-ltx-2-5-duration-N, where N is the billed duration in seconds (1 to 10). For example a 6-second clip bills as inference-ltx-2-5-duration-6.

MiniMax H3

Applies to the MiniMax H3 job types in five tiers:

• Partner – inference.minimax.h3.txt2vid.v1, inference.minimax.h3.img2vid.v1 and inference.minimax.h3.ref2vid.v1 (the hosted MiniMax API)
• Base – inference.minimax.h3.base.txt2vid.v1, inference.minimax.h3.base.img2vid.v1 and inference.minimax.h3.base.ref2vid.v1 (self-hosted, v0 equivalents also bill this way)
• Fast – inference.minimax.h3.fast.txt2vid.v1, inference.minimax.h3.fast.img2vid.v1 and inference.minimax.h3.fast.ref2vid.v1 (self-hosted)
• Turbo / Hyper – inference.minimax.h3.turbo.{txt2vid,img2vid,ref2vid}.v0 and inference.minimax.h3.hyper.{txt2vid,img2vid,ref2vid}.v0 (self-hosted)

All tiers bill per second of output video; output duration runs from 4 to 15 seconds (billed in whole seconds, a job with no duration set bills at the 6-second default). Only Partner takes a resolution of 768P (default) or 2K; Base, Fast, Turbo and Hyper use a fixed 768P-class output spec.

Partner price per video

Resolution	4 s	5 s	6 s	7 s	8 s	9 s	10 s	11 s	12 s	13 s	14 s	15 s
768P	$0.32	$0.40	$0.48	$0.56	$0.64	$0.72	$0.80	$0.88	$0.96	$1.04	$1.12	$1.20
2K	$0.52	$0.65	$0.78	$0.91	$1.04	$1.17	$1.30	$1.43	$1.56	$1.69	$1.82	$1.95

Base price per video

Base is 768P only.

4 s	5 s	6 s	7 s	8 s	9 s	10 s	11 s	12 s	13 s	14 s	15 s
$0.32	$0.40	$0.48	$0.56	$0.64	$0.72	$0.80	$0.88	$0.96	$1.04	$1.12	$1.20

Fast price per video

Fast is 768P only.

4 s	5 s	6 s	7 s	8 s	9 s	10 s	11 s	12 s	13 s	14 s	15 s
$0.32	$0.40	$0.48	$0.56	$0.64	$0.72	$0.80	$0.88	$0.96	$1.04	$1.12	$1.20

Turbo / Hyper price per video

Both tiers share the same latency class and the same prices.

4 s	5 s	6 s	7 s	8 s	9 s	10 s	11 s	12 s	13 s	14 s	15 s
$0.0277	$0.0330	$0.0451	$0.0517	$0.0595	$0.0736	$0.0844	$0.1026	$0.1098	$0.1294	$0.1408	$0.1540

Reference videos on ref2vid jobs are billed at the same per-second rate as the output: the input video’s duration is added to the output duration before pricing (reference video is capped at 15 seconds, so billed durations run to 60 on Partner, Base and Fast, 30 on Turbo and Hyper). Billed durations above 15 seconds continue at the per-second rate, for example (Partner 768P and Base bill identically):

Billed duration	Partner 768P / Base	Partner 2K
20 s	$1.60	$2.60
30 s	$2.40	$3.90
45 s	$3.60	$5.85
60 s	$4.80	$7.80

Input image surcharge

Input images are counted across the reference images on ref2vid jobs and any first or last frame on img2vid jobs. Up to 5 input images are included in the per-second price. From the sixth image onwards a flat $0.04 surcharge per image is added to the whole video, regardless of duration or resolution:

Input images	Surcharge per video
0 to 5	none
6	$0.04
7	$0.08
8	$0.12
9	$0.16

For example, a 6-second Partner ref2vid job with 7 reference images bills $0.48 + $0.08 = $0.56.

Product codes

The product field is inference-minimax-h3[-2k][-M-in]-duration-N for Partner, where M is the number of input images (omitted when there are none) and N is the billed duration in seconds (4 to 60); for example a 6-second job with 7 reference images bills as inference-minimax-h3-7-in-duration-6. The self-hosted tiers carry their tier name in the code instead: inference-minimax-h3-{base,fast}[-M-in]-duration-N (4 to 60) and inference-minimax-h3-{turbo,hyper}[-M-in]-duration-N (4 to 30), for example inference-minimax-h3-fast-7-in-duration-6.

Pruna P-Video

Applies to the P-Video job types:

• inference.pruna.p-video.txt2vid.v1
• inference.pruna.p-video.img2vid.v1
• inference.pruna.p-video.aud2vid.v1

Priced per video by mode (draft: true for Draft, otherwise Standard), resolution and duration. Aspect ratio and prompt do not change the price. Text- and image-to-video take a duration of 5 or 10 seconds; audio-to-video follows the length of the input audio and bills at the 5, 10 or 15 second tier, rounded up.

Price per video

Mode	Resolution	5 seconds	10 seconds	15 seconds
Draft	720p	$0.025	$0.050	$0.075
Draft	1080p	$0.050	$0.100	$0.150
Standard	720p	$0.100	$0.200	$0.300
Standard	1080p	$0.200	$0.400	$0.600

Product codes

The product field follows the pattern inference-pruna-p-video[-1080p][-draft]-duration-N, where N is 5, 10 or 15. 720p and Standard are the defaults and carry no suffix. For example a 10-second Draft video at 1080p bills as inference-pruna-p-video-1080p-draft-duration-10.

Runway Gen-4

Applies to the job type inference.runway.gen4.vid2vid.v1.

Priced as a flat price per video-to-video generation. Input video length, aspect ratio, prompt and seed do not change the price.

Price per video

Price
$0.75

Product codes

The product field is inference-runway-gen4.

Seedance

Applies to the Seedance 1.0 job types, in three tiers:

• Lite – inference.seedance.lite.txt2vid.v1 and inference.seedance.lite.img2vid.v1
• Pro – inference.seedance.pro.txt2vid.v1 and inference.seedance.pro.img2vid.v1
• Pro Turbo – inference.seedance.proturbo.txt2vid.v1 and inference.seedance.proturbo.img2vid.v1

Priced per video by resolution and duration (5 or 10 seconds). Aspect ratio, prompt and seed do not change the price, and image-to-video bills the same as text-to-video.

Price per video

Tier	Resolution	5 seconds	10 seconds
Lite	480p	$0.09	$0.18
Lite	720p	$0.20	$0.40
Lite	1080p	$0.44	$0.88
Pro	480p	$0.12	$0.24
Pro	1080p	$0.61	$1.22
Pro Turbo	480p	$0.048	$0.096
Pro Turbo	1080p	$0.244	$0.488

Pro and Pro Turbo do not offer 720p. When omitted, resolution defaults to 1080p and duration to 5 seconds.

Product codes

The product field follows the pattern inference-seedance-{lite,pro,proturbo}-{480p,720p,1080p}-duration-{5,10}. For example a 10-second Pro Turbo video at 480p bills as inference-seedance-proturbo-480p-duration-10.

Seedance 2.0

Applies to the Seedance 2.0 family of job types, in three tiers:

• Seedance 2.0 – inference.seedance-2.txt2vid.v1 and inference.seedance-2.img2vid.v1
• Seedance 2.0 Fast – inference.seedance-2.fast.txt2vid.v1 and inference.seedance-2.fast.img2vid.v1
• Seedance 2.5 – inference.seedance-2-5.txt2vid.v1 and inference.seedance-2-5.img2vid.v1

Seedance 2.0 and 2.0 Fast are priced per second of output video by resolution. duration is 4 to 15 seconds (default 5); setting duration to -1 lets the model pick the length and the clip bills at its actual duration. Aspect ratio, prompt, seed and audio do not change the price, and image-to-video bills the same as text-to-video.

Price per second

Tier	Resolution	Per second	5 seconds	10 seconds	15 seconds
2.0	480p	$0.062	$0.31	$0.62	$0.93
2.0	720p	$0.14	$0.70	$1.40	$2.10
2.0	1080p	$0.31	$1.55	$3.10	$4.65
2.0 Fast	480p	$0.05	$0.25	$0.50	$0.75
2.0 Fast	720p	$0.07	$0.35	$0.70	$1.05

resolution defaults to 1080p on Seedance 2.0 and to 720p on Seedance 2.0 Fast. Seedance 2.0 Fast does not offer 1080p.

Seedance 2.5 uses a fixed upstream spec (prompt and optional input image only) and bills a flat price per video:

Tier	Price per video
2.5	$1.05

Product codes

Seedance 2.0 bills as inference-seedance-2-{480p,720p,1080p}-duration-N and Seedance 2.0 Fast as inference-seedance-2-fast-{480p,720p}-duration-N, where N is the billed duration in seconds. For example a 10-second Seedance 2.0 video at 1080p bills as inference-seedance-2-1080p-duration-10. Seedance 2.5 bills as inference-seedance-2-5.

Sora 2

Applies to the Sora 2 job types:

• Sora 2 – inference.sora-2.txt2vid.v1 and inference.sora-2.img2vid.v1
• Sora 2 Pro – inference.sora-2.pro.txt2vid.v1 and inference.sora-2.pro.img2vid.v1

Priced per second of output video. duration is 4, 8 or 12 seconds (default 4). Sora 2 renders at 720p; Sora 2 Pro takes a resolution of 720p (default) or 1080p. Aspect ratio, prompt and seed do not change the price, and image-to-video bills the same as text-to-video.

Price per video

Model	Resolution	Per second	4 seconds	8 seconds	12 seconds
Sora 2	720p	$0.10	$0.40	$0.80	$1.20
Sora 2 Pro	720p	$0.30	$1.20	$2.40	$3.60
Sora 2 Pro	1080p	$0.50	$2.00	$4.00	$6.00

Product codes

The product field follows the pattern inference-sora-2-duration-N for Sora 2 and inference-sora-2-pro-{720p,1080p}-duration-N for Sora 2 Pro, where N is 4, 8 or 12. For example an 8-second Sora 2 Pro video at 1080p bills as inference-sora-2-pro-1080p-duration-8.

Tenstorrent Wan 2.2 Lightning

Applies to the job type inference.tenstorrent.wan2-2-lightning.img2vid.v1.

This model runs on Prodia’s own hardware rather than an upstream API, so it carries an internal price: a flat rate per video, independent of duration and settings.

Price per video

Price
$0.084

Product codes

The product field is inference-tenstorrent-wan2-2-lightning.

Veo 3

Applies to the Veo job types:

• Veo 3 Fast – inference.veo.fast.txt2vid.v2 and inference.veo.fast.img2vid.v2 (and their v1 equivalents)
• Veo 3 – inference.veo.txt2vid.v2 and inference.veo.img2vid.v2 (and their v1 equivalents)

Every Veo 3 video is 8 seconds long. Priced per video by tier and whether audio is generated (generate_audio: true). Output resolution (720p or 1080p), prompt and seed do not change the price, and image-to-video bills the same as text-to-video.

Price per video

Model	Length	Without audio	With audio
Veo 3 Fast	8 seconds	$0.80	$1.20
Veo 3	8 seconds	$1.60	$3.20

Product codes

The product field is inference-veo or inference-veo-fast, with -audio appended when audio is generated. Jobs that set aspect_ratio explicitly carry it in the product as well, for example inference-veo-fast-16_9-audio.

Veo 3.1 Lite

Applies to the job types:

• inference.veo.lite.txt2vid.v2
• inference.veo.lite.img2vid.v2

Every Veo 3.1 Lite video is 8 seconds long. Priced per video by resolution (720p, the default, or 1080p) and whether audio is generated (generate_audio: true). Prompt, seed and image-to-video do not change the price.

Price per video

Resolution	Without audio	With audio
720p	$0.24	$0.40
1080p	$0.40	$0.64

Product codes

The product field follows the pattern inference-veo-lite-{720p,1080p}[-audio]-duration-8. For example an 8-second 1080p video with audio bills as inference-veo-lite-1080p-audio-duration-8.

Vidu Q3 Pro

Applies to the Vidu job types:

• inference.vidu-q3-pro.txt2vid.v1
• inference.vidu-q3-pro.img2vid.v1

Vidu Q3 Pro uses a fixed upstream spec (prompt and optional input image only) and bills a flat price per video.

Price per video

Price
$0.50

Product codes

The product field is inference-vidu-q3-pro.

Wan 2.6

Applies to the Wan 2.6 job types:

• Video – inference.wan2-6.txt2vid.v1 and inference.wan2-6.img2vid.v1
• Image – inference.wan2-6.txt2img.v1 and inference.wan2-6.img2img.v1

Video is priced per second of output by resolution. Text-to-video takes a size (width*height) and image-to-video takes a resolution (720P or 1080P, the default); sizes up to 1 MP bill at 720p and larger sizes bill at 1080p. duration runs from 2 to 15 seconds (default 5) and is billed in whole seconds, rounded up. Images are a flat price. Aspect ratio, prompt, seed and reference inputs do not change the price.

Video price per second

Resolution	Per second	5 seconds	10 seconds	15 seconds
720P	$0.084	$0.42	$0.84	$1.26
1080P	$0.14	$0.70	$1.40	$2.10

Image price

Price per image
$0.028

Product codes

Video bills as inference-wan2-6-{720p,1080p}-duration-N, where N is the billed duration in seconds (2 to 15). For example a 5-second 1080P clip bills as inference-wan2-6-1080p-duration-5. Images bill as inference-wan2-6-image.

Wan 2.7

Applies to the Wan 2.7 job types:

• Video – inference.wan2-7.txt2vid.v1, inference.wan2-7.img2vid.v1 and inference.wan2-7.vid2vid.v1
• Image – inference.wan2-7.txt2img.v1 and inference.wan2-7.img2img.v1

Video is priced per second of output by resolution (720P, the default, or 1080P). duration runs from 2 to 15 seconds (default 5) and is billed in whole seconds, rounded up. Video-to-video bills on the output duration. Images are a flat price. Aspect ratio, prompt, seed and reference inputs do not change the price.

Video price per second

Resolution	Per second	5 seconds	10 seconds	15 seconds
720P	$0.07	$0.35	$0.70	$1.05
1080P	$0.105	$0.525	$1.05	$1.575

Image price

Output	Example sizes	Price
1K or 2K	1024×1024, 2048×2048	$0.021

Product codes

Video bills as inference-wan2-7-{720p,1080p}-duration-N, where N is the billed duration in seconds (2 to 15). For example a 5-second 1080P clip bills as inference-wan2-7-1080p-duration-5. Images bill as inference-wan2-7-image.

Wan 3.0

Applies to the Wan 3.0 job types:

• inference.wan3-0.txt2vid.v1
• inference.wan3-0.img2vid.v1

Priced per second of output by resolution (480P, 720P, the default, or 1080P). duration runs up to 30 seconds (default 5) and is billed in whole seconds, rounded up. Aspect ratio, prompt, seed and audio do not change the price, and image-to-video bills the same as text-to-video.

Price per second

Resolution	Per second	5 seconds	10 seconds	15 seconds	30 seconds
480P	$0.035	$0.175	$0.35	$0.525	$1.05
720P	$0.07	$0.35	$0.70	$1.05	$2.10
1080P	$0.14	$0.70	$1.40	$2.10	$4.20

Product codes

The product field follows the pattern inference-wan3-0-{480p,720p,1080p}-duration-N, where N is the billed duration in seconds (1 to 30). For example a 10-second 1080P clip bills as inference-wan3-0-1080p-duration-10.

FLUX.1

Applies to the FLUX.1 job types:

• FLUX.1 [dev] – inference.flux.dev.txt2img.v2, inference.flux.dev.img2img.v2, inference.flux.dev.inpainting.v2 (and their v1 equivalents), plus inference.flux-fast.dev.txt2img.v1
• FLUX1.1 [pro] – inference.flux.pro11.txt2img.v1
• FLUX1.1 [pro] Ultra – inference.flux.pro11ultra.txt2img.v1 and inference.flux.pro11ultra.img2img.v1

FLUX.1 [dev] is priced per image by step count; the FLUX1.1 [pro] models are a flat price per image. Output resolution, prompt and seed do not change the price. Volume pricing applies from 1M generations.

Price per image

Model	Steps	Price	Volume discount
FLUX.1 [dev]	Up to 28	$0.0200	25%
FLUX.1 [dev]	29 to 50	$0.0240	25%
FLUX1.1 [pro]	—	$0.0400	25%
FLUX1.1 [pro] Ultra	—	$0.0600	25%

Product codes

Model	Product
FLUX.1 [dev]	inference-flux-dev-steps-28, inference-flux-dev-steps-50
FLUX1.1 [pro]	inference-flux-pro11
FLUX1.1 [pro] Ultra	inference-flux-pro11-ultra

FLUX.1 Kontext

Applies to the FLUX.1 Kontext job types:

• FLUX.1 Kontext [dev] – inference.flux-fast.dev.kontext.img2img.v1
• FLUX.1 Kontext [pro] – inference.flux-kontext.pro.txt2img.v2 and inference.flux-kontext.pro.img2img.v2 (and their v1 equivalents)
• FLUX.1 Kontext [max] – inference.flux-kontext.max.txt2img.v2 and inference.flux-kontext.max.img2img.v2 (and their v1 equivalents)

Flat price per image. Output resolution, aspect ratio, prompt and seed do not change the price, and image-to-image bills the same as text-to-image. Volume pricing applies from 1M generations.

Price per image

Model	Example sizes	Price	Volume discount
FLUX.1 Kontext [dev]	1024×1024, 1568×672, 672×1568	$0.025	25%
FLUX.1 Kontext [pro]	1024×1024, 1568×672, 672×1568	$0.040	25%
FLUX.1 Kontext [max]	512×512, 512×768, 640×640	$0.080	25%

Product codes

Model	Product
FLUX.1 Kontext [dev]	inference-flux-kontext-dev
FLUX.1 Kontext [pro]	inference-flux-kontext-pro
FLUX.1 Kontext [max]	inference-flux-kontext-max

FLUX.2

Applies to the FLUX.2 job types:

• FLUX.2 [dev] – inference.flux-2.dev.txt2img.v1 and inference.flux-2.dev.img2img.v1 (and their v0 equivalents)
• FLUX.2 [pro] – inference.flux-2.pro.txt2img.v1 and inference.flux-2.pro.img2img.v1
• FLUX.2 [flex] – inference.flux-2.flex.txt2img.v1 and inference.flux-2.flex.img2img.v1
• FLUX.2 [max] – inference.flux-2.max.txt2img.v1 and inference.flux-2.max.img2img.v1

Priced per image by output resolution (in megapixels) and the number of input images (0 to 8). Steps, prompt and seed do not change the price. FLUX.2 [dev] is self-hosted; the [pro], [flex] and [max] tiers are proxied from the upstream API at pass-through rates.

Output resolution buckets (measured as width × height):

Bucket	Pixel budget	Example sizes
Up to 1 MP	≤ 1,048,576	1024×1024, 1536×683
Up to 2 MP	≤ 2,096,704	1448×1448, 2048×1024
Up to 3 MP	≤ 3,140,784	1772×1772, 2560×1229
Over 3 MP	> 3,140,784	2048×2048, 3072×1536

FLUX.2 [dev] price per image

Inputs	Up to 1 MP	Up to 2 MP	Up to 3 MP	Over 3 MP
Text-to-image (no inputs)	$0.012	$0.024	$0.036	$0.048
1 input image	$0.024	$0.036	$0.048	$0.06
2 input images	$0.036	$0.048	$0.06	$0.072
3 input images	$0.048	$0.06	$0.072	$0.084
4 input images	$0.06	$0.072	$0.084	$0.096
5 input images	$0.072	$0.084	$0.096	$0.108
6 input images	$0.084	$0.096	$0.108	$0.12
7 input images	$0.096	$0.108	$0.12	$0.132
8 input images	$0.108	$0.12	$0.132	$0.144

FLUX.2 [pro] price per image

Inputs	Up to 1 MP	Up to 2 MP	Up to 3 MP	Over 3 MP
Text-to-image (no inputs)	$0.03	$0.045	$0.06	$0.075
1 input image	$0.045	$0.06	$0.075	$0.09
2 input images	$0.06	$0.075	$0.09	$0.105
3 input images	$0.075	$0.09	$0.105	$0.12
4 input images	$0.09	$0.105	$0.12	$0.135
5 input images	$0.105	$0.12	$0.135	$0.15
6 input images	$0.12	$0.135	$0.15	$0.165
7 input images	$0.135	$0.15	$0.165	$0.18
8 input images	$0.15	$0.165	$0.18	$0.195

FLUX.2 [flex] price per image

Inputs	Up to 1 MP	Up to 2 MP	Up to 3 MP	Over 3 MP
Text-to-image (no inputs)	$0.06	$0.12	$0.18	$0.24
1 input image	$0.12	$0.18	$0.24	$0.30
2 input images	$0.18	$0.24	$0.30	$0.36
3 input images	$0.24	$0.30	$0.36	$0.42
4 input images	$0.30	$0.36	$0.42	$0.48
5 input images	$0.36	$0.42	$0.48	$0.54
6 input images	$0.42	$0.48	$0.54	$0.60
7 input images	$0.48	$0.54	$0.60	$0.66
8 input images	$0.54	$0.60	$0.66	$0.72

FLUX.2 [max] price per image

Inputs	Up to 1 MP	Up to 2 MP	Up to 3 MP	Over 3 MP
Text-to-image (no inputs)	$0.07	$0.10	$0.13	$0.16
1 input image	$0.10	$0.13	$0.16	$0.19
2 input images	$0.13	$0.16	$0.19	$0.22
3 input images	$0.16	$0.19	$0.22	$0.25
4 input images	$0.19	$0.22	$0.25	$0.28
5 input images	$0.22	$0.25	$0.28	$0.31
6 input images	$0.25	$0.28	$0.31	$0.34
7 input images	$0.28	$0.31	$0.34	$0.37
8 input images	$0.31	$0.34	$0.37	$0.40

Product codes

The product field follows the pattern inference-flux-2-{dev,pro,flex,max}[-N-in]-M-mp, where N is the number of input images (omitted when there are none) and M is the 1 to 4 megapixel bucket. For example an image with 2 input images rendered at 1536×1536 (3 MP) bills as inference-flux-2-pro-2-in-3-mp.

FLUX.2 Klein 4B

Applies to the FLUX.2 Klein 4B distilled job types:

• inference.flux-2.klein.4b.txt2img.v1 and inference.flux-2.klein.4b.img2img.v1
• inference.flux-2.klein.txt2img.v1 and inference.flux-2.klein.img2img.v1 (the default aliases, currently routed to 4B distilled)

Priced per image by output resolution and the number of input images.

Note

These prices take effect on 2026-10-01. Until then the current price sheet applies.

Price per image

Inputs	Up to 1 MP	Up to 2 MP	Up to 3 MP	Over 3 MP
Text-to-image (no inputs)	$0.0005	$0.0027	$0.0040	$0.0059
1 input image	$0.0010	$0.0027	$0.0040	$0.0059
2 input images	$0.0017	$0.0034	$0.0068	$0.0084
3 input images	$0.0025	$0.0065	$0.0078	$0.0084
4 input images	$0.0033	$0.0065	$0.0080	$0.0109
5 input images	$0.0045	$0.0068	$0.0102	$0.0109
6 input images	$0.0054	$0.0088	$0.0116	$0.0132
7 input images	$0.0068	$0.0092	$0.0130	$0.0145
8 input images	$0.0100	$0.0108	$0.0148	$0.0170

FLUX.2 Klein 4B PricingMegapixel bucket thresholds, example sizes and product codes.

Nano Banana

Applies to the Nano Banana and Gemini 3 image job types:

• Nano Banana (Gemini 2.5 Flash) – inference.nano-banana.txt2img.v2, inference.nano-banana.img2img.v2 and inference.nano-banana.img2img.v1
• Nano Banana Pro (Gemini 3 Pro) – inference.gemini-3-pro.txt2img.v1 and inference.gemini-3-pro.img2img.v1
• Nano Banana 2 (Gemini 3.1 Flash) – inference.gemini-3-1-flash.txt2img.v1 and inference.gemini-3-1-flash.img2img.v1

Priced per image by the resolution setting (1K, 2K or 4K). Aspect ratio, prompt and input images do not change the price, and image-to-image bills the same as text-to-image.

Price per image

Model	Resolution	Example sizes	Price
Nano Banana (Gemini 2.5 Flash)	1K	1024×1024, 1568×672, 672×1568	$0.039
Nano Banana Pro (Gemini 3 Pro)	1K or 2K	1024×1024, 1568×672, 2560×1440	$0.150
Nano Banana Pro (Gemini 3 Pro)	4K	3840×2160	$0.300
Nano Banana 2 (Gemini 3.1 Flash)	1K	1024×1024	$0.080
Nano Banana 2 (Gemini 3.1 Flash)	2K	2048×2048	$0.120
Nano Banana 2 (Gemini 3.1 Flash)	4K	3840×2160	$0.160

Nano Banana (Gemini 2.5 Flash) only produces 1K output. resolution defaults to 1K when omitted.

Product codes

Model	Product
Nano Banana (Gemini 2.5 Flash)	inference-nano-banana
Nano Banana Pro (Gemini 3 Pro)	inference-gemini-3-pro, inference-gemini-3-pro-4k
Nano Banana 2 (Gemini 3.1 Flash)	inference-gemini-3-1-flash, inference-gemini-3-1-flash-2k, inference-gemini-3-1-flash-4k

Pruna P-Image

Applies to the job type inference.pruna.p-image-ideogram.txt2img.v1.

Priced per image by thinking level (high, the default, medium, low or very low) and output resolution. image_size is 1K (default) or 2K; setting explicit width/height instead bills by the requested pixel count (over 1 MP bills as 2K). Prompt and seed do not change the price.

Price per image

Thinking	1K	2K
High (default)	$0.015	$0.030
Medium	$0.010	$0.020
Low	$0.0075	$0.015
Very low	$0.003	$0.006

Product codes

The product field is inference-pruna-p-image-ideogram, with -medium, -low or -very-low for the lower thinking levels and -2k appended for 2K output. For example a 2K image at the low thinking level bills as inference-pruna-p-image-ideogram-low-2k.

Qwen Image Edit Plus

Available in two tiers, chosen by job type:

• Speed – inference.qwen.image-edit.plus.lightning.img2img.v2
• Quality – inference.qwen.image-edit.plus.img2img.v1 and inference.qwen.image-edit.plus.lightning.img2img.v1

Priced per generation by output resolution and whether one or several input images are supplied. Steps, prompt and seed do not change the price.

Price per generation

Tier	Inputs	Up to 1 MP	Up to 4 MP
Speed	Single input image	$0.0085	$0.0320
Speed	Multiple input images	$0.0170	$0.0650
Quality	Single input image	$0.0150	$0.0450
Quality	Multiple input images	$0.0300	$0.0900

How the buckets work

Output resolution is measured in pixels (width × height, each 256 to 2048):

Bucket	Pixel range	Example sizes
Up to 1 MP	≤ 1,048,576	1024×1024, 1200×900, 1280×800
Up to 4 MP	> 1,048,576	1600×1200, 1920×1080, 2048×2048

Input images are counted from the images array (1 to 3). Exactly one image bills as single input; two or three bill as multiple inputs.

Product codes

The product field follows the pattern inference-qwen-image-edit-{speed,quality}-{small,large}-{single,multi}, where small is the up-to-1 MP bucket and large is the up-to-4 MP bucket. For example a Speed job with two input images rendered at 1920×1080 bills as inference-qwen-image-edit-speed-large-multi.

Recraft

Applies to the Recraft V3 and Recraft V4 job types. Each is a flat price per generation; size, prompt and style do not change the price.

Price per generation

Model	Output	Job types	Price
V3	Raster image	inference.recraft.txt2img.v1, inference.recraft.img2img.v1	$0.04
V3 Vectors	SVG	inference.recraft.img2vec.v1	$0.08
V4	Raster image	inference.recraft.v4.txt2img.v1	$0.04
V4 Pro	Raster image	inference.recraft.v4.pro.txt2img.v1	$0.25
V4 Vector	SVG	inference.recraft.v4.txt2vec.v1	$0.08
V4 Pro Vector	SVG	inference.recraft.v4.pro.txt2vec.v1	$0.30

V3 and V4 render up to about 1 MP (for example 1024×1024 or 2048×1024 for V3, 768×1536 or 1024×1024 for V4). V4 Pro renders up to about 4 MP (for example 2048×2048 or 1536×3072).

Product codes

Model	Product
V3	inference-recraft
V3 Vectors	inference-recraft-img2vec
V4	inference-recraft-v4
V4 Pro	inference-recraft-v4-pro
V4 Vector	inference-recraft-v4-vector
V4 Pro Vector	inference-recraft-v4-pro-vector

SDXL

Applies to the SDXL job types inference.sdxl.txt2img.v1, inference.sdxl.img2img.v1 and inference.sdxl.inpainting.v1.

Priced per image by step count. Output resolution (512 to 1536 per side), prompt and seed do not change the price, and image-to-image and inpainting bill the same as text-to-image.

Price per image

Steps	Example sizes	Price
Up to 25	1024×1024, 768×1024, 1024×768	$0.0020
26 to 50	1024×1024, 768×1024, 1024×768	$0.0025
51 and above	1024×1024, 768×1024, 1024×768	$0.0100

Product codes

The product field is inference-sdxl-steps-25, inference-sdxl-steps-50 or inference-sdxl-steps-100 for the three step buckets.

Seedream

Applies to the Seedream job types:

• Seedream 4.0 – inference.seedream-4.txt2img.v1 and inference.seedream-4.img2img.v1
• Seedream 4.5 – inference.seedream-4-5.txt2img.v1 and inference.seedream-4-5.img2img.v1
• Seedream 5.0 Lite – inference.seedream-5-0.lite.txt2img.v1 and inference.seedream-5-0.lite.img2img.v1

Flat price per image at any supported resolution. Output size, prompt, seed and input images do not change the price, and image-to-image bills the same as text-to-image.

Price per image

Model	Example sizes	Price
Seedream 4.0	1024×1024, 2048×2048, 4096×4096	$0.030
Seedream 4.5	1024×1024, 2048×2048, 4096×4096	$0.040
Seedream 5.0 Lite	1024×1024, 2048×2048	$0.035

Product codes

Model	Product
Seedream 4.0	inference-seedream-4
Seedream 4.5	inference-seedream-4-5
Seedream 5.0 Lite	inference-seedream-5-0-lite

Topaz Gigapixel

Applies to the job type inference.topaz.gigapixel-standard-2.upscale.v1.

Priced by the output resolution of the upscaled image. The caller may set width/height (up to 32,000 per side); when omitted, Topaz determines the output size. The price follows the actual output pixel count of the delivered image. Upstream this bills as 1 credit per 24 MP of output.

Price per image

Output megapixels	Price
Up to 24 MP	$0.10
Up to 48 MP	$0.20
Up to 72 MP	$0.30
Up to 96 MP	$0.40
Up to 128 MP	$0.60
Up to 256 MP	$1.00
Over 256 MP	$1.60

Product codes

The product field is inference-topaz-gigapixel-standard-2, with the suffix for the output megapixel tier appended: -48mp, -72mp, -96mp, -128mp, -256mp or -512mp. For example an upscaled image with 60 MP of output bills as inference-topaz-gigapixel-standard-2-72mp.

Topaz Proteus

Applies to the job type inference.topaz.proteus.upscale.v1.

Priced per second of output video by the output resolution tier. The upscale scale is 2 or 4 (default 2), or an explicit width/height (up to 16,000 per side); the tier follows the actual output size of the delivered clip (up to ~1 MP bills as 720p, up to ~2.1 MP as 1080p, larger as 4k). Clip length is billed in whole seconds, rounded up, to 30 seconds.

Price per second of output

Output resolution	Per second	10 seconds	30 seconds
720p	$0.01	$0.10	$0.30
1080p	$0.02	$0.20	$0.60
4k	$0.06	$0.60	$1.80

Product codes

The product field follows the pattern inference-topaz-proteus-{720p,1080p,4k}-duration-N, where N is the billed clip length in seconds (1 to 30). For example a 10-second 1080p upscale bills as inference-topaz-proteus-1080p-duration-10.

Image Utilities

Fixed-price utility jobs. Each bills a single flat product per call; input image size, prompt and other settings do not change the price. Volume pricing applies from 1M generations.

Price per generation

Utility	Model	Job type	Price	Volume discount
Background removal	BiRefNet 2	inference.remove-background.v1	$0.0025	25%
NSFW image detection	ViT	inference.vit.img2label.v2	$0.0002	—
Upscale 2×	R-ESRGAN	inference.upscale.v1 with upscale: 2	$0.0010	25%
Upscale 4×	R-ESRGAN	inference.upscale.v1 with upscale: 4	$0.0020	25%
Upscale 8×	R-ESRGAN	inference.upscale.v1 with upscale: 8	$0.0030	25%
Upscale 2×	HYPIR	inference.hypir.upscale.v1	$0.0500	25%
Face restore	GFPGAN	inference.facerestore.v1	$0.0008	25%
Segmentation	SAM 3 (Segment Anything 3)	inference.sam3.segment.v1	$0.0050	25%

Product codes

Utility	Product
Background removal	inference-background-removal
NSFW image detection	inference-vit-nsfw
Upscale (R-ESRGAN)	inference-upscale-2x, inference-upscale-4x, inference-upscale-8x
Upscale (HYPIR)	inference-hypir-upscale-v1
Face restore	inference-facerestore
Segmentation	inference-sam3

Job PricingRetrieve the exact cost of a job with the price query parameter.

Tracking Job CostsMonitor spend across jobs and tokens.