Do reference images guarantee character or style consistency?

Do reference images guarantee character or style consistency? — Audio availability is experimental and is not guaranteed; inspect every result manually before delivery.

AI video model

Google

Veo

Veo3.1 Fast

Q: Is Kyeo's Veo3.1 Fast the same as Google's official Fast model?

Is Kyeo's Veo3.1 Fast the same as Google's official Fast model? — This page describes the current verified on-site contract and does not expose or rely on an internal provider model identifier.

Q: How many images does `REFERENCE_2_VIDEO` support?

How many images does `REFERENCE_2_VIDEO` support? — Reference mode accepts 1–3 verified JPEG or PNG images, only 16:9 or 9:16, and requires an 8-second duration.

Q: Why are 1080p and 4K not base parameters?

Why are 1080p and 4K not base parameters? — Resolution follow-up actions require an owned successful 720p base task or Extend result; a direct 1080p or 4K result cannot request another resolution action.

Q: Can I use text-only generation now?

Can I use text-only generation now? — Text-only, first/last-frame and one-to-three-reference-image paths are selected from the submitted images.

Q: How many credits do base generation and Extend use?

How many credits do base generation and Extend use? — Direct generation costs 30 credits at 720p, 38 at 1080p (37.5 rounded up), and 90 at 4K. Extend costs 30; eligible 1080p and 4K result actions cost 8 and 60.

Veo3.1 Fast on Kyeo AI supports text, first/last-frame and reference-image generation, direct 720p/1080p/4K selection, and 4/6/8-second duration controls. 30 / 38 / 90 credits by resolution.

Workflows

TEXT / FRAME / REFERENCE

Credit cost

720p 30 · 1080p 38 · 4K 90

Prompt limit

5,000 characters

Upload limit

JPEG / PNG · 1–3 · 10 MB

Text-only, first/last-frame and one-to-three-reference-image paths are selected from the submitted images. TEXT_2_VIDEO / FIRST_AND_LAST_FRAMES_2_VIDEO / REFERENCE_2_VIDEO.

Direct generation costs 30 credits at 720p, 38 at 1080p (37.5 rounded up), and 90 at 4K. Extend costs 30; eligible 1080p and 4K result actions cost 8 and 60. 720p / 1080p / 4K.

Reference mode accepts 1–3 verified JPEG or PNG images, only 16:9 or 9:16, and requires an 8-second duration. REFERENCE_2_VIDEO.

Audio availability is experimental and is not guaranteed; inspect every result manually before delivery. 4 / 6 / 8 s.

Use this model View credit pricing Back to Model Hub

30-second overview

Veo

30 / 38 / 90 credits by resolution

What it does best

This is Kyeo's current public source Fast integration page, not a complete mirror of Google's official Veo 3.1 Fast API.

Best for

Use it to validate one text, first/last-frame, or reference-image path with non-critical inputs, then evaluate result operations separately after the base task succeeds.

At a glance

What is this model like?

Text-only, first/last-frame and one-to-three-reference-image paths are selected from the submitted images. Direct generation costs 30 credits at 720p, 38 at 1080p (37.5 rounded up), and 90 at 4K. Extend costs 30; eligible 1080p and 4K result actions cost 8 and 60.

What it does best

This is Kyeo's current public source Fast integration page, not a complete mirror of Google's official Veo 3.1 Fast API.

Best for

Use it to validate one text, first/last-frame, or reference-image path with non-critical inputs, then evaluate result operations separately after the base task succeeds.

Why use it on Kyeo AI

Kyeo AI presents Veo's available controls, credit cost, and result workflow together, making it easier to compare options and begin creating.

Key facts

Quickly assess whether this model fits your use case.

Also known as

The same model may appear under different names across documentation and community discussions; this list keeps them easy to search and compare.

Veo3.1 Fast

Google Veo

Veo Video

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

How do I use Veo3.1 Fast?

What is Veo3.1 Fast REFERENCE_2_VIDEO?

Veo3.1 Fast pricing

Veo3.1 Fast vs Quality

Veo3.1 Fast vs Lite

How many reference images can Veo3.1 Fast use?

What does Veo3.1 Fast Extend do?

What does Veo3.1 Fast Get 1080P do?

What does Veo3.1 Fast Get 4K do?

How does Kyeo AI's Veo3.1 Fast differ from Google's stable Fast model?

Selection guide

Use these decision points when choosing a model.

When a controlled test makes sense

When you need to validate one specific path in Kyeo's current Fast interface and are willing to use non-critical media to confirm the request, callback, result, and credit charge, start with the smallest sample.

When to compare another model

Compare Lite for a lower local base charge. Sora 2 Pro is now a Legacy workflow and should not be a default delivery baseline.

Minimum verification path

Minimum verification path: Before delivery, verify the selected mode, duration, actual dimensions, audio, URL lifetime and billed credits with a non-sensitive sample.

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

How does Veo3.1 Fast differ from Veo3.1 Lite?

Veo3.1 Fast vs Veo3.1 Lite

How does Veo3.1 Fast differ from Veo3.1 Quality?

Veo3.1 Fast vs Veo3.1 Quality

How does Veo3.1 Fast differ from Sora 2 Pro?

Veo3.1 Fast vs Sora 2 Pro

Model comparison

Compare the current model with alternatives at a glance.

Role in Kyeo AI

Veo3.1 Fast

Full local Veo workflow with three input paths and result actions

Veo3.1 Lite

Lightweight base-generation tier

Veo3.1 Quality

High-quality generation tier

Generation modes

Veo3.1 Fast

text + first-and-last-frame + reference image

Veo3.1 Lite

Base text and image video

Veo3.1 Quality

Base text/image video without reference mode

Post-result actions

Veo3.1 Fast

Shows Extend / 1080p / 4K after a successful task

Veo3.1 Lite

No current Extend or resolution actions

Veo3.1 Quality

Also supports result actions

Local base charge

Veo3.1 Fast

30 / 38 / 90 credits by resolution

Veo3.1 Lite

Fixed 15 credits

Veo3.1 Quality

Fixed 225 credits

Current validation priority

Veo3.1 Fast

Verify one base path and its task lifecycle first

Veo3.1 Lite

Low-barrier concept sample

Veo3.1 Quality

Current validation priority — Veo3.1 Quality: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.

Practical usage insights

Practical guidance based on public sources, current on-site limits, and representative tasks.

Veo: Fast to explore

Veo: Fast to explore: This page describes the current verified on-site contract and does not expose or rely on an internal provider model identifier.

Base requests and result actions require separate accounting

Base requests and result actions require separate accounting: Direct generation costs 30 credits at 720p, 38 at 1080p (37.5 rounded up), and 90 at 4K. Extend costs 30; eligible 1080p and 4K result actions cost 8 and 60.

Capabilities

Three input paths in the current site form

Three input paths in the current site form: Text-only, first/last-frame and one-to-three-reference-image paths are selected from the submitted images.

Reference mode is a Kyeo product choice

Reference mode is a Kyeo product choice: Reference mode accepts 1–3 verified JPEG or PNG images, only 16:9 or 9:16, and requires an 8-second duration.

Result actions depend on a Kyeo-owned source task

Result actions depend on a Kyeo-owned source task: Resolution follow-up actions require an owned successful 720p base task or Extend result; a direct 1080p or 4K result cannot request another resolution action.

Use cases

Veo: Everyday creation

Veo: Everyday creation: Before delivery, verify the selected mode, duration, actual dimensions, audio, URL lifetime and billed credits with a non-sensitive sample.

Reference-driven video

Reference-driven video: Reference mode accepts 1–3 verified JPEG or PNG images, only 16:9 or 9:16, and requires an 8-second duration.

Verify result operations after base success

Verify result operations after base success: Resolution follow-up actions require an owned successful 720p base task or Extend result; a direct 1080p or 4K result cannot request another resolution action.

Prompt tips

Select `generationType` before refining the prompt

Decide whether the brief begins from text, first/last frames, or reference images. A long prompt cannot compensate for choosing the wrong media workflow.

Assign each reference image a clear role

When using one to three reference images, label whether each image provides the subject, styling, or visual style, then check for roles that were mixed up or omitted.

Treat upscaling and extension as separate steps

They are separate actions on a successful task with additional charges. Higher resolution does not guarantee better content, motion, or detail.

Why choose it

Text-only, first/last-frame and one-to-three-reference-image paths are selected from the submitted images. 4 / 6 / 8 s.

Reference mode accepts 1–3 verified JPEG or PNG images, only 16:9 or 9:16, and requires an 8-second duration. 1–3 JPEG / PNG.

Direct generation costs 30 credits at 720p, 38 at 1080p (37.5 rounded up), and 90 at 4K. Extend costs 30; eligible 1080p and 4K result actions cost 8 and 60. 30 / 38 / 90.

Resolution follow-up actions require an owned successful 720p base task or Extend result; a direct 1080p or 4K result cannot request another resolution action. 720p / Extend.

What to know first

Reference mode accepts 1–3 verified JPEG or PNG images, only 16:9 or 9:16, and requires an 8-second duration. Auto.

Resolution follow-up actions require an owned successful 720p base task or Extend result; a direct 1080p or 4K result cannot request another resolution action. 1080p / 4K.

Audio availability is experimental and is not guaranteed; inspect every result manually before delivery. Resolution follow-up actions require an owned successful 720p base task or Extend result; a direct 1080p or 4K result cannot request another resolution action.

Before delivery, verify the selected mode, duration, actual dimensions, audio, URL lifetime and billed credits with a non-sensitive sample. 10 MB.

Adjustable parameters

Quickly assess whether this model fits your use case.

Generation mode

generationType

Optional

Parameter type: select

Depends on submitted images

TEXT_2_VIDEO

FIRST_AND_LAST_FRAMES_2_VIDEO

REFERENCE_2_VIDEO

Aspect ratio

aspectRatio

Optional

Parameter type: select

Default: 16:9

Landscape (16:9)

Portrait (9:16)

Auto crop (Auto)

Resolution

resolution

Optional

Parameter type: select

720p

720p — 30

1080p — 38

4K — 90

Duration

duration

Optional

Parameter type: select

8 s

4 s

6 s

8 s

Watermark text

watermark

Optional

Parameter type: text

Prompt translation

enableTranslation

Optional

Parameter type: select

Default: true

Auto-translate to English

Keep original text

Credit usage

30 / 38 / 90 credits by resolution

Direct generation costs 30 credits at 720p, 38 at 1080p (37.5 rounded up), and 90 at 4K. Extend costs 30; eligible 1080p and 4K result actions cost 8 and 60.

Budget tip

Before batch generation, run an A/B test with the same assets across the current model and alternatives to validate quality and avoid wasting credits.

FAQ

Related models

Compare these similar candidates before deciding.

Veo3.1 Lite

Veo3.1 Lite on Kyeo AI supports text, first/last-frame and reference-image generation, direct 720p/1080p/4K selection, and 4/6/8-second duration controls. 15 / 23 / 75 credits by resolution.

AI video model

15 / 23 / 75 credits by resolution

View details Use now

Veo3.1 Quality

Veo 3.1 Quality on Kyeo accepts text or one to two first/last-frame images through the public source Veo 3.1 Quality route for 225 credits. Eligible results can launch Extend, 1080p, or 4K actions separately. Quality is a workflow name, not a fixed delivery guarantee.

AI video model

225 / 233 / 285 credits by resolution

View details Use now

Seedance 2.0

Seedance 2.0 / Capabilities — Text accepts no media; frames requires a first frame and allows a last frame; reference requires a prompt and at least one image, video, or audio reference. Reference media cannot be sent with endpoint-frame fields. Seedance 2.0 supports three mutually exclusive text, frame, and multimodal-reference scenes. The current callable output set is 720p, 1080p, and 4K for 4–15 seconds; video-reference requests are available only at 1080p or 4K because those are the current priced combinations. 164–3,840 credits per request

AI video model

164–3,840 credits per request

View details Use now