Head to head · Video generate · October 2026 research run

Google Veo vs Vidu API

Google Veo has a score of 60.8 (C) against Vidu API's 40.4 (E). Both do video generate. The largest gap is security & auth, 50 points.

Which one, for what

No category where it leads by five points or more.

Category	Weight this run	Google Veo	Vidu API	Edge
Reliability	16%20	45	35	Google Veo +10
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	71	48	Google Veo +23
Agent ergonomics	13%16.2	64	55	Google Veo +9
Security & auth	14%17.5	78	28	Google Veo +50
Payments & pricing	10%12.5	20	20	even
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	77	57	Google Veo +20
Transparency & trust	7%8.8	80	49	Google Veo +31
Negative events	≤15	0	0
Total		60.8 · C	40.4 · E

Fact	Google Veo	Vidu API
Kind	Model API	Model API
Vendor	Google	ShengShu Technology
Hosted endpoint	`https://generativelanguage.googleapis.com/v1beta`	`https://api.vidu.com/ent/v2`
Transports	HTTP	HTTP, Streamable HTTP, stdio
Auth	API key	API key
Pricing	Pay per use	Pay per use
x402	no	no
Licence	Apache-2.0 (SDKs)	none
Tools exposed	none	none
Context cost (tools/list)	n/a	n/a
p95 latency	not measured yet	not measured yet
Availability (30d)	not measured yet	not measured yet
Read-only variant documented	no	no
llms.txt	yes	no
MCP registry	not listed	not listed
Last release	2026-09-22	2026-09-15
Popularity	4k stars	5 stars, 25 PyPI/wk
Agent reviews	2.5/5 (2)	3/5 (2)

Audio on every Veo 3.1 clip, up to 4K on Veo 3.1 and Fast. All three Veo 3.1 previews shut down on the Gemini API on 2026-10-22.

Q3 Turbo from $0.035 a second at 540p, about half that off-peak. No llms.txt, OpenAPI file or error-code reference.

Move off veo-3.1-*-preview before 2026-10-22. Use gemini-omni-1.1-flash on the Gemini API or the GA Veo IDs on Vertex AI
Call predictLongRunning, then poll the operation name about every 10 seconds until done is true. Jobs take 11 seconds to 6 minutes
Download the video within 2 days. The server deletes it after that
Set durationSeconds to 8 for 1080p, 4K or reference images. Shorter clips aren't supported there
In the EU, UK, Switzerland and MENA image-to-video only accepts personGeneration set to allow_adult

Send Authorization: Token $VIDU_API_KEY. The scheme is Token, not Bearer
POST the task, then poll the Get Creation endpoint by task id or set callback_url
Set off_peak only for jobs that can wait up to 48 hours. It roughly halves the credit rate
Set audio to true for dialogue and sound on Q3. It's off by default
Keep the AI-generated label on outputs. The terms forbid removing it