AI video models · compared
Kling 4.0 vs Kling 4.0 Flash
Kling 4.0 and Kling 4.0 Flash are both AI video models that run on one varg API key. This page puts what the varg catalog states about each side by side: the price, how it is billed, the limits of the input, what it takes and the typical time. It ranks neither on quality.
- Kling 4.0
- From $0.48 per run from $0.157/s
- Kling 4.0 Flash
- From $0.38 per run $0.126/s
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01.
Kling 4.0 vs Kling 4.0 Flash: side by side
Every row is read from the varg catalog and each model's input schema. A "from" price is the cheapest request the catalog states for that model, at its own cheapest settings. For the exact price of a request, send its body to POST https://api.varg.ai/v2/estimate.
| Fact | Kling 4.0 | Kling 4.0 Flash |
|---|---|---|
| Made by | Kuaishou | Kuaishou |
| Takes and makes | Text to video, Image to video, Video to video | Text to video, Image to video, Video to video |
| Price | From $0.48 per run | From $0.38 per run |
| Rates on the cheapest route | Resolution 1080p: $0.235/s; Other: $0.157/s; Minimum charge: $0.471 | Per second: $0.126/s; Minimum charge: $0.378 |
| Billed | per second | per second |
| Clip length | 3 to 30 s | 3 to 20 s |
| Resolutions you can set | 720p, 1080p | 720p |
| Audio switch | Yes: "audio": true asks for a native audio track | No: the input schema says the model ignores "audio" |
| Typical time | ~3 min | ~2 min |
| Routes | 9 on fal | 4 on fal |
| Model id | kling_v4 | kling_v4_flash |
Which to pick
Each line is a difference between two rows of the table. None of it says which model's output looks better: that depends on the prompt.
Pick Kling 4.0 when
- you need a clip longer than 20 seconds: it takes up to 30 in one request.
- you need 1080p: the tiers Kling 4.0 Flash's input lists stop at 720p.
Pick Kling 4.0 Flash when
- you want the lower starting price: from $0.38 per run, against from $0.48 per run, each at the model's own cheapest settings.
- you want the lower starting rate: $0.126/s, against from $0.157/s; the table gives each model's rate by setting.
- you want the shorter typical wait: ~2 min, against ~3 min, by the catalog's estimates.
Call Kling 4.0 and Kling 4.0 Flash
One endpoint and one API key for both: POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed.
Kling 4.0
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling_v4",
"prompt": "A detective in a black trench coat stands on a rooftop in the rain, looking through a telescope.",
"duration": 5
}'vargai call_tool --tool video '{"model":"kling_v4","prompt":"A detective in a black trench coat stands on a rooftop in the rain, looking through a telescope.","duration":5}'Kling 4.0 Flash
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling_v4_flash",
"prompt": "A detective in a black trench coat stands on a rooftop in the rain, looking through a telescope.",
"duration": 5
}'vargai call_tool --tool video '{"model":"kling_v4_flash","prompt":"A detective in a black trench coat stands on a rooftop in the rain, looking through a telescope.","duration":5}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
Kling 4.0 vs Kling 4.0 Flash: questions
- Which is cheaper, Kling 4.0 or Kling 4.0 Flash?
- Kling 4.0 Flash starts lower: from $0.38 per run, against from $0.48 per run for Kling 4.0. By starting rate, Kling 4.0 Flash is lower: Kling 4.0 from $0.157/s, Kling 4.0 Flash $0.126/s. Those are each model's cheapest settings, and the price of a request depends on what it asks for: the table lists each model's rates. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which makes longer clips, Kling 4.0 or Kling 4.0 Flash?
- Kling 4.0: up to 30 seconds in one request, against 20 for Kling 4.0 Flash, by their input schemas.
- Which resolutions can I set on Kling 4.0 and Kling 4.0 Flash?
- Kling 4.0: 720p, 1080p. Kling 4.0 Flash: 720p. These are the tiers the "resolution" field of each model's input schema lists; a model can also have a default size that is not one of them.
- Can I use Kling 4.0 and Kling 4.0 Flash with one API key?
- Yes. Both run on varg behind POST https://api.varg.ai/v2/tools/video/call with one API key and one credit balance: send "model": "kling_v4" or "model": "kling_v4_flash". Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01.