theserverless.dev InferenceList

Models

Showing 1–24 of 24 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
fal × Clear
Model Provider Modality Input ↑ Output Context
H3 Max Turbo Image to Video fal video $0.0163/second Not published— —
H3 Max Turbo Text to Video fal video $0.0163/second Not published— —
FLUX 3 Max Image to Video fal video $0.0213/second Not published— —
Seedance 2.5 US Image to Video fal video $0.0214/1000 tokens Not published— —
Seedance 2.5 US Reference to Video fal video $0.0214/1000 tokens Not published— —
Gemini Omni Flash 1.1 Image to Video fal video $0.03/second Not published— —
H3 Max Image to Video fal video $0.0325/second Not published— —
MiniMax H3 Max Text to Video fal video $0.0325/second Not published— —
H3 Max Lip Sync Image to Video fal video $0.05/second Not published— —
H3 Max Reference to Video fal video $0.05/second Not published— —
MiniMax H3 Image to Video fal video $0.05/second Not published— —
MiniMax H3 Reference to Video fal video $0.05/second Not published— —
Wan 3.0 fal video $0.05/second Not published— —
Wan 3.0 fal video $0.05/second Not published— —
Kling AI Avatar v2 Standard fal video $0.0562/second Not published— —
Kling Video fal video $0.07/second Not published— —
Kling Video v2.6 Image to Video fal video $0.07/second Not published— —
Kling O3 Edit Video [Pro] fal video $0.14/second Not published— —
Kling Video v3 Image to Video [Pro] fal video $0.14/second Not published— —
Kling Video v3 Image to Video [Standard] fal video $0.14/second Not published— —
Kling 4.0 Image to Video fal video $0.157/second Not published— —
Kling 4.0 Reference to Video fal video $0.157/second Not published— —
Bytedance Seedance V1.5 Pro Image To Video fal video $1.2/1m tokens Not published— —
sync-3 Lipsync fal video $8/minute Not published— —

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.