Loading model…正在加载模型详情…
Loading model…正在加载模型详情…
Create a video scene from text with Kling 2.6, which Kling AI describes as a model for coordinated visuals, speech and sound.
Visual: In a fashion live-streaming room, clothes hang on a rack, and a full-length mirror reflects the host's figure. Dialog: [African-American female host] turns to show off the sweatshirt fit. [African-American female host, cheerful voice] says: "360-degree flawless cut, slimming and flattering." Immediately, [African-American female host] moves closer to the camera. [African-American female host, lively voice] says: "Double-sided brushed fleece, 30 dollars off with purchase now."
A clean live-streaming desk, with props such as a crystal glass and wooden blocks neatly arranged. The makeup brush lightly sweeps across the crystal glass and wooden blocks, producing a "shh-shh" sound. The camera focuses on the props and the details of the action.
Kling 2.6 is a video generation model from Kuaishou’s Kling AI. Kling AI describes it as an audiovisual model that aligns action with speech, ambient sound and sound effects.
UniRoute offers the text-to-video variant with a duration option. Write the scene you want to see, choose a clip duration and review the quote before running the request.
Kling 2.6 follows Kling 2.5 Turbo. Kling AI’s description of this version emphasizes generating visuals and sound together; UniRoute currently exposes a text prompt and duration, without separate sound or aspect-ratio controls.
What you can do with Kling 2.6 through UniRoute today.
Describe the subject, action, setting and camera movement, then choose a duration to turn the scene into a clip.
Other Kling 2.6 modes (image-to-video) aren’t available on UniRoute yet.
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| Kling 2.6 Text to Video | kling-2.6/text-to-video | Text to video | Text prompt and an option for duration | Duration: 5s, 10s | $0.34 to $0.69 per request |
Priced per request. The option you choose sets the price.
| Option | Official API | UniRoute | Save |
|---|---|---|---|
| 5s | $0.35 | $0.34375 | Save 2% |
| 10s | $0.70 | $0.6875 | Save 2% |
Official price: kling.ai
Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
Call Kling 2.6 from your own code with the media API.
# Requires bash, curl and jq. Set API_KEY to your own unified UniRoute Key.set -euo pipefail: "${API_KEY:?Set API_KEY first}"BASE='https://api.uniroute.app/v1/media'MODEL='kling-2.6/text-to-video'OPTION='5'PROMPT='A calm sunrise over a mountain lake'curl -fsS --max-time 60 "$BASE/catalog" -H "Authorization: Bearer $API_KEY" | jq -e '.data.models'BODY=$(jq -n --arg model "$MODEL" --arg option "$OPTION" --arg prompt "$PROMPT" '{model:$model,option:$option,prompt:$prompt}')QUOTE_BODY=$(printf '%s' "$BODY" | jq '{model,option}')QUOTE=$(curl -fsS --max-time 60 "$BASE/quote" -H "Authorization: Bearer $API_KEY" -H 'Content-Type: application/json' -d "$QUOTE_BODY")CAP=$(printf '%s' "$QUOTE" | jq -er '.data.quoted_usd')BODY=$(printf '%s' "$BODY" | jq --arg cap "$CAP" '. + {max_cost_usd:$cap}')IDEMPOTENCY="example-$(date +%s)-$$"create() { curl -fsS --max-time 60 "$BASE/tasks" -H "Authorization: Bearer $API_KEY" -H "Idempotency-Key: $IDEMPOTENCY" -H 'Content-Type: application/json' -d "$BODY"; }TASK_ID=$(create | jq -er '.data.task_id')# The same request and idempotency key must return the original task without charging again.REPLAY_ID=$(create | jq -er '.data.task_id')[ "$TASK_ID" = "$REPLAY_ID" ]for attempt in $(seq 1 120); do TASK=$(curl -fsS --max-time 60 "$BASE/tasks/$TASK_ID" -H "Authorization: Bearer $API_KEY") printf '%s' "$TASK" | jq -e '.data | {task_id,status,billing}' if printf '%s' "$TASK" | jq -e '.data.status == "success" and .data.billing.state == "charged"' >/dev/null; then index=0 while IFS= read -r url; do index=$((index+1)) curl -fL --max-time 120 "$url" -o "$TASK_ID-$index.bin" done < <(printf '%s' "$TASK" | jq -er '.data.urls[].url') break fi if printf '%s' "$TASK" | jq -e '.data.status == "failed" and .data.billing.state == "released"' >/dev/null; then exit 1; fi if [ "$attempt" = 120 ]; then echo "Polling limit reached. Keep task ID $TASK_ID and query it later; do not create a new task." >&2 exit 1 fi sleep 5donecurl -fsS --max-time 60 "$BASE/tasks?limit=20" -H "Authorization: Bearer $API_KEY" | jq -e '.data'# Check this task and the caller Key in Console usage; billing.charged_usd is the actual USD charge.| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
option | Body | One of the options offered for the model: 5, 10. |
prompt | Body | Text prompt describing what to generate. |
max_cost_usd | Body | Maximum cost in USD for this task, taken from the quote. |
Idempotency-Key | Header | A unique key per task, so a repeated request returns the original task instead of charging again. |
Typical ways to put Kling 2.6 to work.
Describe a product demonstration or campaign scene to explore a visual direction before planning a shoot.
Turn a written interaction into a video draft, then refine the characters, action and camera direction in your prompt.
Explore the movement of objects and materials with detailed descriptions of gestures, framing and scene atmosphere.
Use the media API for prompt-based video creation, with a quote before submission and an asynchronous task for each clip.
Common questions about Kling 2.6.
Kling 2.6 is Kling AI’s video generation model. On UniRoute you can use its text-to-video variant from this page or through the media API.
The available variant takes a text prompt and a duration option. The specs and pricing tables show all duration choices; the API section lists the accepted parameters.
No. Kling AI’s model description includes native audio, but UniRoute currently exposes no separate sound or aspect-ratio setting for this variant.
From $0.34 / clip. The price covers the whole clip at the duration you choose. The Pricing section lists every option, with prices updated 2026-11-08.
Request a quote for the model and option, create a media task with an Idempotency-Key and a maximum cost, then poll until the video is ready. The API section shows a complete example.
No. Generation is paid from your wallet balance. You can open the workspace and review the price without paying, create an account to see a live quote for your exact settings, and you are charged only for requests that are accepted.