Veo 2

google-deepmind/veo-2 · by Google DeepMind · Diffusion transformer (DiT)

Pricing — 1 offering(s)

Google DeepMind (Gemini API)

About this offering: Retired: Google shut down Veo 2 (veo-2.0-generate-001) on 2026-06-30, so the price shown is its last published rate. It generated video from text or an image, without audio. Google pointed users to Veo 3.1 (preview) or the generally available video models on its Gemini Enterprise Agent Platform.

Standard

Retired — no longer sold · last price $0.35 / second, until 2026-06-29

$0.35 / second Historical 2026-06-13 → 2026-06-29

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

See how Veo 2 fits into a cost-aware routing setup

Capability profile

How Veo 2 rates across core capability dimensions, with the task-level evidence behind each rating.

Prompt adherence Strong

temporal consistency Strong

motion quality Strong

native audio Weak

No audio generation; Veo 3 adds this capability.

Resolution ceiling Moderate

Max 1080p; no 4K.

Inference speed Moderate

clip duration ceiling Moderate

Max 8 seconds per clip.

cost efficiency Moderate

video editing Weak

T2V and I2V only via Gemini API; no editing of existing clips.

Operator guidance

Retired: Google shut down Veo 2 on 2026-06-30. It was the lower-cost, no-audio option next to Veo 3 ($0.35 vs $0.40 per second). For new work, look at Veo 3.1 (preview) or another current video model.

Use cases

High-quality T2V when audio is not required
Cost-effective alternative to Veo 3 Standard ($0.35/s vs $0.40/s)
Image-to-video animation of reference images

Limitations

No native audio
Max 8 seconds per clip
Superseded by Veo 3 for most use cases; the $0.05/s gap may not justify using Veo 2