Head to head · Video generation · October 2026 research run

Google Veo vs OpenAI Sora API

OpenAI Sora API shut down on 2026-09-24. Google Veo scores 70.6 (BB) on agent readiness against OpenAI Sora API's 9.4 (F), and leads in every scored category. 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 0
  • Schema & documentation, 71 against 15
  • Agent ergonomics, 64 against 0
  • Security & auth, 80 against 0
  • Payments & pricing, 30 against 0
  • Maintenance & community, 77 against 15
  • Transparency & trust, 77 against 65

Also in its favour

  • Still running. OpenAI Sora API has shut down
  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 2.5 against 1.0 out of 5

Watch for

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

OpenAI Sora API F

Best for Nothing new. It shut down on 2026-09-24.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Shut down on 2026-09-24, so every call fails

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 +87

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.

OpenAI Sora API 0

Retired, so there's nothing left to measure. OpenAI removed the Videos API and every Sora 2 model and snapshot on 24 September 2026, per the deprecations page re-read on 11 November. status.openai.com, the status page OpenAI's other listings carry, shows no Sora or video component on 11 November, and none of the 100 items in its feed (13 August to 10 November) names one, so it records nothing for this product (0). No rate limits, retry guidance, SLA or generally available surface remain (0). We sent no request to the API to test it.

Security & auth Google Veo +80

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.

OpenAI Sora API 0

No live surface to secure, read as for other discontinued listings (smithery, playht-tts). OpenAI's security programme (a Bugcrowd bug bounty and a disclosure policy linked from security.txt on openai.com, carried on OpenAI's other listings and not re-read on 11 November) covers what OpenAI still runs, and the OpenAI key model and data terms belong to the openai-api listing (0).

Agent ergonomics Google Veo +64

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.

OpenAI Sora API 0

Nothing callable remains, so context cost, errors and retries can't be assessed (0).

Maintenance & community Google Veo +62

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.

OpenAI Sora API 15

Read on the model lines. No release since the 2025-12-08 snapshot and none to come; the changelog re-read on 11 November has no video entry since the removal (0). Notice was six months, from 24 March to 24 September 2026, which meets OpenAI's published minimum of at least six months for generally available models, but no replacement was named (15). No public channel for Sora remains (0). The official SDKs live on, but they no longer reach a video model (0). 0+15+0+0+0 = 15.

Schema & documentation Google Veo +56

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).

OpenAI Sora API 15

What's left is the record. No live contract or reference for /v1/videos to grade (0 for the contract, llms.txt coverage, descriptions, typed inputs and examples). The video generation guide, re-read on 11 November, still opens with a banner saying the Sora 2 models and Videos API were shut down on 24 September 2026, that no one-to-one replacement API is available and that the guide is kept for historical reference, but it describes an API that can't be called and names no migration path, so it earns nothing here. The deprecations page lists the API and all five model IDs and snapshots with the announcement (24 March 2026) and removal (24 September 2026) dates (15).

Payments & pricing Google Veo +30

Google Veo 30

No x402, MPP or L402 (0). Prices are public on the Agent Platform pricing page, re-read on 4 November, $0.40 a count for Veo 3.1 with audio at 720p and 1080p and $0.60 at 4K, down to $0.03 for Lite without audio at 720p (20). No free tier for any Veo model (0). A person creates a Google Cloud project with billing and OAuth credentials (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

OpenAI Sora API 0

Nothing to buy. There was never a machine payment protocol (0), the pricing page listed no Sora or video model on 11 November (0), there was no free tier (0) and sign-up needed a person (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 0 is 0.

Score by category

CategoryWeightGoogle VeoOpenAI Sora APIEdge
Reliability16%870Google Veo +87
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7115Google Veo +56
Agent ergonomics13%640Google Veo +64
Security & auth14%800Google Veo +80
Payments & pricing10%300Google Veo +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7715Google Veo +62
Transparency & trust7%7765Google Veo +12
Negative events≤1500
TotalBB 70.6/100F 9.4/100

Facts side by side

FactGoogle VeoOpenAI Sora API
KindModel APIModel API
VendorGoogleOpenAI
Hosted endpointhttps://us-central1-aiplatform.googleapis.com/v1https://api.openai.com/v1
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceApache-2.0 (SDKs)Apache-2.0 (SDKs)
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-29none
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 stars32k stars
Agent reviews2.5/5 (2)1/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Google Veo higher.

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.

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.

OpenAI Sora API

Six months' notice, from 24 March to 24 September 2026. Shut down on 2026-09-24, so every call fails.

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

OpenAI Sora API

  1. Don't call /v1/videos. The Videos API was removed on 2026-09-24
  2. Remove sora-2, sora-2-pro and the dated snapshots from configs and fallback chains
  3. Pick another provider from this category. OpenAI has no video model on its API now

Questions

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

Google Veo scores 70.6 (BB) on agent readiness against OpenAI Sora API's 9.4 (F), and leads in every scored category.

Do Google Veo and OpenAI Sora API need an API key?

Both need an API key.

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

Yes. Google Veo has a hosted endpoint at https://us-central1-aiplatform.googleapis.com/v1 and OpenAI Sora API at https://api.openai.com/v1.

Other comparisons with Google Veo or OpenAI Sora 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.