MODEL REFERENCE / KLING AI

Kling VIDEO 3.0
verified model reference.

Kling AI video generation model supporting text-to-video, image-to-video, multis-shot storyboards, character element references and optional native audio.

Not publishedcontext not published
Not publishedmax output
2026-10-12last verified

PRIMARY-SOURCE VERIFIED

Kling VIDEO 3.0 at a glance.

Kling AI does not publish a token context window for this service. Input modalities: text + image. Output: video + audio. Pricing status: No direct Standard price published.

MODEL IDkling-3.0
CONTEXT WINDOWNot published
MAX OUTPUTNot published
KNOWLEDGE CUTOFFNot published
STANDARD RATENot publishedper generation task (official credits vary by second, resolution and audio)
OUTPUT RATE—not-published

CAPABILITY CONTRACT

Published model behavior.

REASONING

Not published

Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.

INPUT

text + image

Input modalities come from the cited official model documentation.

OUTPUT

video + audio

Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.

PRICING STATUS

No direct Standard price published.

No direct Standard price published.

SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.

CAVEATS

What the source record does not assume.

01

The official developer API provides /text-to-video/kling-3.0 and supports both 720p/1080p/4K video settings; product and developer-plan access or pricing may differ.

02

Official creative product reference pricing: 720p without native audio 6 Credits/second, 720p with audio 9 Credits/second; 1080p without audio 8 Credits/second, 1080p with audio 12 Credits/second. Voice control adds 2 Credits/second. These are product CREDITS, not USD.

03

An exact public Standard USD-denominated developer API rate was not established from the official references. No credit-to-USD conversion is asserted and no flat USD rate is published in SXF.

04

Duration is documented as 3–15 seconds in the official user guide. Video output is not a token-generation output limit; no artificial context window or max_output tokens are claimed.

05

Reference credit rates come from Kling AI's consumer-facing creative plan, not a verified USD-denominated developer API tariff.

EXPLORE

Keep the model in context.

OFFICIAL SOURCES

Verification links.

WHAT CHANGED

Kling VIDEO 3.0: what changed.

No post-baseline factual changes recorded for Kling VIDEO 3.0 since 2026-10-12.

VERIFIED BASELINE2026-10-12Current facts remain aligned with the SXF ledger.

VERIFIED CHANGE HISTORY

Kling VIDEO 3.0 verified history.

Open ledger JSON ↗
BASELINE

Kling VIDEO 3.0

Baseline verified: context not published · Not published max output

Official evidence ↗

Append-only SXF ledger · 1 verified event · chain head a805f17ab1ad…

COMPARE KLING VIDEO 3.0

Put this model in context.

Open Compare Engine ↗