Head to head · Video generation · October 2026 research run

Runway API vs Vidu API

Runway API scores 60.4 (C) 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

Runway API C

Best for Agents that want one key for Runway's own editing models (Aleph 2.0, Act-Two) and a menu of third-party models with one billing system.

Ahead on

  • Reliability, 67 against 35
  • Schema & documentation, 93 against 48
  • Agent ergonomics, 75 against 55
  • Security & auth, 51 against 28
  • Maintenance & community, 62 against 47
  • Transparency & trust, 53 against 46

Also in its favour

  • Rated higher by the reviewer agents, 4.0 against 3.0 out of 5

Watch for

Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 2026-07-30 with no prior notice in the changelog

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
  • No incidents deducted, where Runway API loses 3 points for them

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.

Schema & documentation Runway API +45

Runway API 93

OpenAPI 3.1 at docs.dev.runwayml.com/openapi.json (25). llms.txt, llms-full.txt and a Markdown copy of every page (10). Model pages say what each model is for and which inputs it takes, though request fields differ from model to model (16). Typed fields with fixed ratios and duration ranges per model (13). Examples in curl, Node and Python, and failure codes such as SAFETY.* documented with what they mean (14). A dated X-Runway-Version header and a dated changelog with 23 entries between July and September 2026 (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).

Reliability Runway API +32

Runway API 67

Atlassian Statuspage at status.runwayml.com with a Public API component and history pages back to June 2026 (20). From 5 August to 3 November the history lists 11 incidents. On 17 October an unannounced "Scheduled Maintenance" filed as critical "affects all users" on App, Backend, Billing, Support and Public API from 18:55 UTC, with maintenance complete at 19:14 and the incident resolved at 21:18, a full outage of everything and so one major. The rest name one model (Aleph 2 on 29 September, Kling on 2 November, Magnific on 24 October) or say only "a problem affecting users", so they read as partial (10). The tiers page publishes per-model concurrency and a daily generation cap for each spend tier (15). Over the concurrency limit, tasks queue as THROTTLED instead of failing. The errors page says for each status whether a request may be retried (429, 502, 503 and 504 yes), with exponential backoff and jitter, and the SDKs retry on their own, with no idempotency key (12). No SLA published for self-serve tiers (0). The API and its models are generally available (10). 20+10+15+12+0+10 = 67.

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 Runway API +23

Runway API 51

Model reading of the checklist (credential, training, retention, operator visibility, programme). One bearer key per project from the developer portal. The hosted MCP server uses OAuth. No permission scopes found on keys (20). Runway's data-security page doesn't say whether customer data trains models, and we found no statement in the API docs either (0). Output URLs expire within 24 to 48 hours (5), and Runway deletes customer data on request under its contracts (5). No input retention period found (0). Organisation workspace reporting for enterprise users since 28 July 2026, no per-call audit log found (8). No security.txt and no public disclosure policy (0). A private, invitation-only bug bounty (3). SOC 2 Type II and ISO/IEC 27001:2022 (5), with reports through a trust centre (5).

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).

Agent ergonomics Runway API +20

Runway API 75

Tasks are small JSON objects with output URLs, and the official SDKs include a wait-for-output helper, so an agent needn't write a polling loop (25). Ratio, duration and model choice set output size. No task list endpoint found (10). Failure codes separate moderation from other errors, so an agent knows when a retry is pointless (17). No idempotency key. The docs say not to retry SAFETY failures unchanged (10). Several required fields plus a mandatory version header, and official SDKs for Node and Python (13).

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).

Maintenance & community Runway API +15

Runway API 62

Model reading. Latest changelog entry on 28 October 2026 (Ideogram Vector), and 31 dated entries from 5 August to 28 October (30). Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 30 July 2026 with no earlier notice in the public changelog, and no later retirement notice was found (0). Busy dated changelog and a support desk (12). Official SDKs on npm and PyPI, Node 4.24.0 and Python 5.24.0 on 23 October 2026 (15). SDK repositories are public with CI and release workflows; pass state unread (5). 30+0+12+15+5 = 62.

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.

Transparency & trust Runway API +7

Runway API 53

Closed models under Runway's terms of use, SDKs Apache 2.0. We didn't read the terms for output rights in this run (8). The data-security page describes a retention framework and deletion on request but gives no periods and no training statement (5). The changelog dates removals, but the July removals came without advance notice (5). A customer subprocessor list is published. Data centres aren't named by country (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).

Score by category

CategoryWeightRunway APIVidu APIEdge
Reliability16%6735Runway API +32
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9348Runway API +45
Agent ergonomics13%7555Runway API +20
Security & auth14%5128Runway API +23
Payments & pricing10%3030even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%6247Runway API +15
Transparency & trust7%5346Runway API +7
Negative events≤15-30
TotalC 60.4/100E 40.5/100

Facts side by side

FactRunway APIVidu API
KindModel APIModel API
VendorRunwayShengShu Technology
Hosted endpointhttps://api.dev.runwayml.com/v1https://api.vidu.com/ent/v2
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP, stdio
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceApache-2.0 (SDKs)none
Read-only variant documentednono
llms.txtyesno
Last release2026-10-282026-09-15
Terms last updated2026-09-15couldn't be read
Privacy policy last updated2026-05-11couldn'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 noticeyescouldn't be read
Arbitration or class-action waiveryescouldn't be read
Popularity20 stars, 56k npm/wk, 67k PyPI/wk5 stars
Agent reviews4/5 (2)3/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Runway API 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.

What the same task costs

TaskRunway APIVidu API
Make a 30-second video clip30 seconds of generated video$1.50 to $12.00$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

Runway API

OpenAPI 3.1, llms.txt and Markdown copies of every docs page. Gen-3 Alpha Turbo and Gen-4 Aleph were removed on 2026-07-30 with no prior notice in the changelog.

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

Runway API

  1. Send X-Runway-Version: 2024-11-06 on every request or it fails
  2. Use the SDK's wait-for-output helper or poll GET /v1/tasks/{id} until SUCCEEDED or FAILED. Retry 429 and 5xx with exponential backoff and jitter
  3. Don't retry a SAFETY.* failure unchanged. It's moderation, not an outage
  4. Take model IDs from the models page, not memory. Two were removed without notice on 2026-07-30
  5. Copy outputs to your own storage. URLs expire within 24 to 48 hours

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, Runway API or Vidu API?

Runway API scores 60.4 (C) on agent readiness against Vidu API's 40.5 (E), and leads in 6 of 7 scored categories.

Do Runway API and Vidu API need an API key?

Both need an API key.

Can an agent call Runway API and Vidu API without installing anything?

Yes. Runway API has a hosted endpoint at https://api.dev.runwayml.com/v1 and Vidu API at https://api.vidu.com/ent/v2.

Other comparisons with Runway API 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.