KlemetKlemet home page
VideoImageSpeechStudioNewPricingMCPDocs
Sign inSign up
VideoLTX-2.5Wan 2.2
ImageFLUX.2 kleinQwen-Image
SpeechVoxCPM2
CreditsIncludedQuestions

Pricing

Open weights on our own cards, from $0.003 an image and $0.018 for five seconds of video. Billed per second, per image or per million characters, with no plan and no seat.

Get an API key

Video

Billed by the second of video, at the resolution you ask for.2 models

LTX-2.5

Lightricks

Lightricks' open weight world model, which generates synchronized video and audio from text or from an image. We run the distilled transformer in full bf16 precision with its Gemma 4 12B text encoder on RTX PRO 6000s, on the fixed 8 step schedule Lightricks ships. Hugging Face keeps the weights behind a contact agreement, so running them yourself means accepting their licence first.

from$0.004per second$1 buys 55 clips of 5 s at 480pRun it
ResolutionKlemetfal
480p$0.004—
720p$0.007—
1080p$0.018$0.06
1440pnot yet$0.12
4Knot yet$0.24
  • 480p$0.004fal —
  • 720p$0.007fal —
  • 1080p$0.018fal $0.06
  • 1440pnot yetfal $0.12
  • 4Knot yetfal $0.24

A five second clip at 1080p costs $0.09 here, $0.30 at fal.

  • fal · LTX-2.3 text-to-video · seen 2026-09-15
  • Replicate · lightricks/ltx-video · seen 2026-09-15 · billed by machine time, about $0.049 a run
License
ltx-2.x-community-license-agreement
Limits
Up to 8 s per render, 24 fps
Runs on
RTX PRO 6000

Wan 2.2

Alibaba Wan-AI

Alibaba's Wan 2.2 in its five billion parameter size, Apache-2.0, run from the diffusers build its authors publish. It renders picture only: there is no audio track, where our LTX tier renders sound with the image.

from$0.049per second$1 buys 4 clips of 5 sRun it
ResolutionKlemetNovitafalReplicate
1280 x 704$0.049$0.10$0.05$0.25
  • 1280 x 704$0.049Novita $0.10fal $0.05Replicate $0.25

A five second clip at 1280 x 704 costs $0.245 here, $0.50 at Novita.

  • Novita · Wan 2.5 text-to-video · seen 2026-09-15 · Wan 2.5, a later release than the 2.2 we run
  • fal · Wan 2.5 · seen 2026-09-15 · one rate, every resolution
  • Replicate · wan-2.1-i2v · seen 2026-09-15 · Wan 2.1, image to video
License
apache-2.0
Limits
1280 x 704, 24 fps, 4 to 8 s per render, no audio
Runs on
H100

Image

Billed by the image, at the size you ask for.2 models

FLUX.2 klein

Black Forest Labs

The four billion parameter FLUX.2, the size Black Forest Labs publishes under Apache-2.0. Their larger builds carry licences we do not accept, so this is the one we run.

from$0.003per image$1 buys 333 imagesRun it
SizeKlemetDeepInfraReplicate
Standard, up to 1024 px$0.003$0.014$0.025
Large, up to 1536 px$0.006$0.032$0.025
Max, up to 2048 px$0.012$0.056$0.025
  • Standard, up to 1024 px$0.003DeepInfra $0.014Replicate $0.025
  • Large, up to 1536 px$0.006DeepInfra $0.032Replicate $0.025
  • Max, up to 2048 px$0.012DeepInfra $0.056Replicate $0.025

Ten images at 2048 px cost $0.12 here, $0.56 at DeepInfra.

  • DeepInfra · FLUX-2-klein-4b · seen 2026-09-15 · billed by surface, $0.014 x (w/1024) x (h/1024)
  • Replicate · black-forest-labs/flux-dev · seen 2026-09-15 · FLUX dev, one rate whatever the size
License
apache-2.0
Limits
Up to 2048 on the long side, sides divisible by 64
Runs on
H100

Qwen-Image

Alibaba Qwen

Alibaba's Apache-2.0 image model, and the one in this catalogue that writes readable text inside a picture. It is also the heaviest, which is what its price says.

from$0.029per image$1 buys 34 imagesRun it
SizeKlemetfal
Standard, up to 1024 px$0.029$0.021
Large, up to 1536 px$0.061$0.047
Max, up to 2048 px$0.13$0.084
  • Standard, up to 1024 px$0.029fal $0.021
  • Large, up to 1536 px$0.061fal $0.047
  • Max, up to 2048 px$0.13fal $0.084

Ten images at 2048 px cost $1.30 here, $0.84 at fal.

  • fal · Qwen · seen 2026-09-15 · billed per megapixel, at $0.02
License
apache-2.0
Limits
Up to 2048 on the long side, sides divisible by 64
Runs on
H100

Speech

Billed by the million characters of script.1 model

VoxCPM2

OpenBMB

OpenBMB's tokenizer free, diffusion autoregressive text to speech model, Apache-2.0 and free for commercial use. Its model card states 2B parameters, 30 languages and 48 kHz output. We run it on a single L40S and charge the card time a narration actually takes.

from$26.50per M characters$1 buys 37k charactersRun it
VoiceKlemetNovita
Any length$26.50$15
  • Any length$26.50Novita $15

A ten thousand character script costs $0.265 here, $0.15 at Novita.

  • Novita · Text to Speech · seen 2026-09-15 · a different model, and ours runs at 48 kHz
Example coming
License
apache-2.0
Limits
Up to 40,000 characters per request, 48 kHz output
Runs on
L40S

Credits

You load a balance and spend it, render by render. There is no plan, no seat and nothing that renews on its own.

  • $10555 clips of 5 s, or 3333 images
  • $251388 clips of 5 s, or 8333 images
  • $502777 clips of 5 s, or 16666 images

Any amount between $5 and $500 works. We run open weights on on-demand cards and take a small margin over the card time, which is the whole reason these prices are what they are.

Included, at no extra cost

No subscription
You load a balance and spend it. Nothing renews.
The price you see
What the page says is what leaves your balance.
Refused, refunded
If the engine refuses a render, the charge comes back.
Open weights
Every licence is named and linked, on every model.
One queue
There is no paid fast lane. Nobody passes in front.
Render from Claude
The MCP endpoint bills the same balance.

Questions

What happens if a render fails?
If the engine refuses the request, the amount is credited back to your balance the same second. Every movement is listed under Activity.
Does the resolution change the price?
Yes. A second of 1080p holds the card about two and a half times longer than a second of 480p, and the rate follows. Every step is in the table above, before you run anything.
Is there VAT on top?
VAT not applicable, article 293 B of the French General Tax Code
Is there a minimum per render?
A small one. Loading the weights costs the same whether the clip runs one second or eight, so a render never bills below that floor. It is already in the table: the shortest clip is where the rate and the floor meet.
Do credits expire?
Your balance stays until you spend it. We do not clear it on a timer.
Why is the first render after a pause slower?
A card that has been idle has to load the weights again, which adds a few tens of seconds. It costs you nothing extra: you pay per second of video, not per second of card.
Can I switch models without changing my code?
Yes. One endpoint, one body, and the model is a field. Swap the slug and nothing else moves.
Every price on this page, through one endpoint.Get an API key
KlemetKlemet home page

Video, images and voice from open weight models, priced per model.

© 2026 Klemet

Product

  • Pricing
  • Video
  • Image
  • Speech
  • Studio

Account

  • Overview
  • Keys
  • Credits

Developer

  • Documentation
  • API reference

Legal

  • Terms of Service
  • Privacy Policy
  • Refund Policy
  • Acceptable Use Policy
  • Cookie Policy
  • Legal Notice

Klemet

  • About
  • Sign in
  • Create an account
Contact us
  • Home
  • Pricing
  • Create
  • Studio
  • Sign in