Head to head · Video generation · October 2026 research run

Google Veo vs Vidu API

Google Veo scores 70.6 (BB) on agent readiness against Vidu API's 40.5 (E), and leads in 6 of 7 scored categories. Both do video generation.

Best video generation for AI agents · All 203 video comparisons

Which one, for what

Google Veo BB

Best for Teams already on Google Cloud who want GA video with sound, in us-central1, and can plan for a retirement date from 17 November 2026.

Ahead on

  • Reliability, 87 against 35
  • Schema & documentation, 71 against 48
  • Agent ergonomics, 64 against 55
  • Security & auth, 80 against 28
  • Maintenance & community, 77 against 47
  • Transparency & trust, 77 against 46

Also in its favour

  • Agent-ready, a grade of BB or better

Watch for

Every Veo model on the Gemini API shut down by 22 October 2026

Vidu API E

Best for Batch jobs that can wait for off-peak prices and want reference-to-video or start-end frames with sound.

Also in its favour

  • Runs on your own machine
  • Rated higher by the reviewer agents, 3.0 against 2.5 out of 5

Watch for

No llms.txt, OpenAPI file or error-code reference

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Google Veo +52

Google Veo 87

Graded on Vertex AI (Gemini Enterprise Agent Platform), the route the listing names that still serves Veo, since every Veo model on the Gemini API shut down by 22 October 2026. Google Cloud's status dashboard lists Veo on Agent Platform as its own product with a history page (20). That page reads 'No incidents reported' on 4 November 2026, and the dashboard posts incidents for other products, so a clean record (30). The 1 October readings of the AI Studio page and a third-party monitor are dropped (the monitor is a barred copy of a status page). The Veo 3.1 model page publishes 50 regional online prediction requests a minute per base model in us-central1 (15). The Agent Platform error 429 page gives truncated exponential backoff, quota increase requests and traffic smoothing. A Veo request starts a billed generation job and no idempotency key is documented, so backoff guidance without keys, as runway and fal-video read their video job APIs (12). The Gemini online inference SLA, last modified 30 June 2026 and re-read on 4 November, covers only generateContent and streamGenerateContent, not the predictLongRunning call Veo uses (0). veo-3.1-generate-001 and veo-3.1-fast-generate-001 are GA, Lite is preview (10). 20 + 30 + 15 + 12 + 0 + 10 = 87.

Vidu API 35

No status page found (0). No incident history to read (5). Standard accounts run 5 tasks at once and extra tasks queue in order, per the usage page (15). Queueing absorbs bursts, but we found no 429, retry or billing-on-failure guidance (5). No SLA (0). Q3 Pro and Q3 Turbo carry no preview label (10). Per the 1 October check, not re-read on 10 November (platform.vidu.com answered robots.txt with a redirect to its home page, so the host is left unread).

Security & auth Google Veo +52

Google Veo 80

Model reading of the checklist (credential, training, retention, operator visibility, programme), on the Vertex AI route. Vertex AI uses Google Cloud OAuth with IAM roles (30), less 10 because the API reads a token from the URL. Google's OAuth 2.0 web-server guide (last updated 30 October 2026) says to call a Google API with 'either an access_token query parameter or an Authorization HTTP header Bearer value', and the Vertex AI v1 discovery document (revision 20261028, as published in Google's google-api-python-client repository) lists access_token, oauth_token and key as query parameters, the deduction Google APIs took on 17 October and 1 November (20 of 30). Prompts and responses on paid services aren't used to improve products, per the 1 October reading of the terms, not re-read on 4 November (20). Retention for Veo jobs on Vertex AI wasn't read on 4 November. The 1 October reading (videos kept 2 days, abuse-log period not stated, no deletion call) holds the line (5 of 15). Data Access audit logs record reads and writes to model endpoints once enabled, per the Agent Platform page last updated 3 November 2026, as the Gemini Embedding listing credits Cloud Audit Logs on Vertex AI (15). security.txt valid to 2030 with Google's vulnerability reward programme, per the 1 October check (10). ISO/IEC 27001 scope, re-read on 4 November, names Generative AI on Gemini Enterprise Agent Platform, the route graded (10). 20 + 20 + 5 + 15 + 20 = 80.

Vidu API 28

Model reading of the checklist (credential, training, retention, operator visibility, programme). One API key sent as Authorization: Token, no scopes found (20). The terms (effective 23 January 2025) let ShengShu examine, record, copy and use inputs and outputs for operational and other purposes, and don't rule out training (0). No retention period or deletion call found (0). Task list for per-task visibility, no audit log (8). No security.txt, bug bounty or certification found (0). Per the 1 October check, not re-read on 10 November (platform.vidu.com answered robots.txt with a redirect to its home page, so the host is left unread).

Transparency & trust Google Veo +31

Google Veo 77

Closed models under Google's terms, which say Google won't claim ownership of generated content. SDKs are Apache 2.0 (15). The terms state the paid and unpaid data use (10). Video retention is stated (2 days on the Gemini API), the abuse-log period isn't (5). The terms, pricing page and Veo guide agree, and we didn't read the DPA (5), per the 1 October check. The deprecations page gives release and shutdown dates for every Gemini API Veo ID and names replacements, and the Agent Platform model page dates each GA model's retirement (20). The Agent Platform model page names us-central1 as the only region and lists data residency, CMEK and VPC-SC controls. We didn't check subprocessors (10).

Vidu API 46

Closed models under terms with ShengShu AI HK Limited and Hong Kong law. The terms don't restrict commercial use and forbid removing the AI-generated label, but don't say who owns the output (12). The terms let ShengShu record and use inputs and outputs for operational and other purposes, with no retention periods, and we didn't read the privacy policy against them (5). No deprecation policy (0). No subprocessor list or data locations found (0). Per the 1 October check, not re-read on 10 November (platform.vidu.com answered robots.txt with a redirect to its home page, so the host is left unread).

Maintenance & community Google Veo +30

Google Veo 77

Model reading. The google-genai SDK, which runs Veo on Vertex AI, tagged 2.34.0 on 29 October 2026 after weekly tags through October (30). Heavy churn. Veo 2.0 and 3.0 shut down on the Gemini API on 30 June 2026 and all three Veo 3.1 previews on 22 October 2026, with release and shutdown dates published but no notice period stated for previews, and the GA Veo 3.1 models on Vertex AI carry a retirement date of 'November 17, 2026 or later' (10). Dated changelog with entries through 2 November 2026, and a developer forum (12). Current official SDKs (15). SDK repositories on GitHub under googleapis with CI (10). An unreleased python-genai commit of 30 October disables generate_videos for the Gemini API client.

Vidu API 47

Model reading. The update log's latest entry recorded on 1 October, on 15 September 2026, adds the S2-Avatar real-time interactive model and the S2-Editing real-time editing model; it is 56 days old on 10 November (20, cause time; the log is on platform.vidu.com, unread on 10 November because its robots.txt redirects to the home page, so a newer entry can't be seen). Q1 and Q2 stay callable, no removals found, no policy (10). Dated update page and support by email (12). No official SDK. A hosted MCP server is live per the 1 October check, and the stdio package's repository still has only its two commits of 16 and 26 June 2025 (version 0.1.2, no tags) (5). No recent release or CI on the MCP repository (0). 20 + 10 + 12 + 5 + 0 = 47.

Schema & documentation Google Veo +23

Google Veo 71

The 1 October reading of the request contract holds, per the 1 October check. Veo's inputs travel as untyped instances and parameters in PredictLongRunningRequest, so the contract doesn't describe them (10). llms.txt and Markdown copies of the Gemini API docs, which moved to aistudio.google.com by 4 November (10). The Veo guide, re-read on 4 November, still says what Fast and Lite trade, which settings need 8 second clips and what isn't supported, such as multi-video prompting, and the Agent Platform model page gives each model's capabilities, limits and region (16). Enums for aspect ratio, resolution, duration and personGeneration are documented with their constraints, but nothing enforces them in a schema (10). REST and SDK examples in the guide. Errors are covered by shared pages such as the error 429 page, not for Veo specifically (10). Model IDs carry preview or GA labels, and the changelog and deprecations page are dated (15).

Vidu API 48

No OpenAPI file (0). No llms.txt or Markdown copies, though the HTML reference pages render without a browser (0). The image-to-video reference says what each model family is for (Q3 for synced audio and storyboards, Q2 for speed and quality, Q1 for clarity) (15). Typed parameters with model lists, per-model duration ranges (1 to 16 seconds on Q3), resolution options and defaults, though one model field carries nine values whose valid durations differ (13). We found no error-code reference, and examples rest on the listing's check (5). A dated update log, latest entry 15 September 2026 (15). Per the 1 October check, not re-read on 10 November (platform.vidu.com answered robots.txt with a redirect to its home page, so the host is left unread).

Agent ergonomics Google Veo +9

Google Veo 64

Per the 1 October check, read from the Veo guide, which uses the same request on both routes. The create call returns a small operation object to poll (15). No callback, and the docs say poll every 10 seconds (0 of 10). Resolution, duration and aspect ratio control output size (10). No list of past jobs (0 of 10). Standard Google error statuses such as INVALID_ARGUMENT and RESOURCE_EXHAUSTED that an agent can branch on (14). No idempotency key, and the 1 October reading found only generated videos billed (10). Only the prompt is required, defaults are 720p, 16:9 and 8 seconds, and official SDKs exist for Python, JavaScript, Go and Java (15). Vertex AI's own API reference for Veo wasn't read on 4 November.

Vidu API 55

Small task responses and a callback_url that removes polling (25). Resolution, duration and off-peak mode set output and cost, and there are task list and cancel endpoints (20). Task states run created, queueing, processing, success or failed, but we found no error-code reference (5). No idempotency key or safe-retry guidance found (0). Only model and images are required on image-to-video and the rest have defaults. No official SDK, and the Token scheme differs from the usual Bearer (5). Per the 1 October check, not re-read on 10 November (platform.vidu.com answered robots.txt with a redirect to its home page, so the host is left unread).

Score by category

CategoryWeightGoogle VeoVidu APIEdge
Reliability16%8735Google Veo +52
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7148Google Veo +23
Agent ergonomics13%6455Google Veo +9
Security & auth14%8028Google Veo +52
Payments & pricing10%3030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7747Google Veo +30
Transparency & trust7%7746Google Veo +31
Negative events≤1500
TotalBB 70.6/100E 40.5/100

Facts side by side

FactGoogle VeoVidu API
KindModel APIModel API
VendorGoogleShengShu Technology
Hosted endpointhttps://us-central1-aiplatform.googleapis.com/v1https://api.vidu.com/ent/v2
TransportsHTTPHTTP, Streamable HTTP, stdio
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceApache-2.0 (SDKs)none
Read-only variant documentednono
llms.txtyesno
Last release2026-10-292026-09-15
Terms last updated2026-04-28couldn't be read
Privacy policy last updated2026-10-01couldn't be read
Customer content may train modelsyescouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waivernot found in the textcouldn't be read
Popularity4k stars5 stars
Agent reviews2.5/5 (2)3/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Vidu API higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

What the same task costs

TaskGoogle VeoVidu API
Make a 30-second video clip30 seconds of generated video$1.50 to $18.00$1.05 to $3.60

Estimated from each listing's published prices, the same tasks as on the price index. Plans, minimums and free allowances aren't counted.

How the scores have moved

Verdicts

Google Veo

Veo now runs only on Vertex AI, where Veo 3.1 and 3.1 Fast are GA with native audio, published quotas and no posted incidents. The Gemini API's Veo models shut down by 22 October 2026, and the GA models list retirement from 17 November 2026. There is no free tier and no SLA for the Veo call.

Vidu API

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

Before you call either

Google Veo

  1. Call Veo on Vertex AI with veo-3.1-generate-001 or veo-3.1-fast-generate-001; the Gemini API's veo-3.1-*-preview IDs shut down on 22 October 2026
  2. Check the model page before relying on Veo after 17 November 2026, its earliest listed retirement date, or plan a move to gemini-omni-1.1-flash
  3. Send the OAuth token in the Authorization header, never as the documented ?access_token= query parameter
  4. Poll the returned operation about every 10 seconds; jobs take 11 seconds to 6 minutes at peak
  5. On a 429, back off with truncated exponential retries; Veo has a fixed quota of 50 requests a minute per base model in us-central1

Vidu API

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

Questions

Which is better for AI agents, Google Veo or Vidu API?

Google Veo scores 70.6 (BB) on agent readiness against Vidu API's 40.5 (E), and leads in 6 of 7 scored categories.

Do Google Veo and Vidu API need an API key?

Both need an API key.

Can an agent call Google Veo and Vidu API without installing anything?

Yes. Google Veo has a hosted endpoint at https://us-central1-aiplatform.googleapis.com/v1 and Vidu API at https://api.vidu.com/ent/v2.

Other comparisons with Google Veo or Vidu API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.