kling/kling-v3-omni
Kling Image 3.0 Omni, served direct from Kling.
Text-to-image and image-to-image with up to 10 reference pictures, 1 to 9 single images or, from reference pictures, a series of 2 to 9, at 1k, 2k or 4k.
Send Kling's own image fields at the top level of the body; the gateway sets model_name. $0.028 per image delivered at 1k or 2k, $0.056 at 4k, never more than n (or series_amount for a series).
| Slug | kling/kling-v3-omni |
| Kind | image |
| Vendor | kling |
| Endpoint | POST /v1/kling/generations |
Charged per job from what the generator reports it rendered — your Logs show the exact figure for each one; see balance and billing.
Calling it
curl https://api.sociaro.com/v1/kling/generations \
-H "Authorization: Bearer $SOCIARO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling/kling-v3-omni",
"prompt": "a paper boat on a rain-soaked street",
"resolution": "1k",
"aspect_ratio": "1:1"
}'
# then poll the job id it returns:
curl https://api.sociaro.com/v1/kling/generations/JOB_ID \
-H "Authorization: Bearer $SOCIARO_API_KEY"Parameters
Kling Image 3.0 Omni — images from text and reference pictures, single or as a series
| Field | Type | Required | Default | Values | What it does |
|---|---|---|---|---|---|
prompt | string | yes | — | text, up to 2500 characters | What to draw. Name a reference picture in it as `<<<image_1>>>` (the first in `image_list`). |
image_list | object[] | no | — | up to 10 × {"image": public https url} | Reference pictures: jpg, jpeg or png, up to 10 MB, at least 300 px. |
resolution | string | no | 1k | 1k · 2k · 4k | `4k` costs twice `1k` and `2k`. |
result_type | string | no | single | single · series | `single`: `n` independent images. `series`: a set of related images, `series_amount` of them. Kling's capability map lists series for image-to-image only: send an `image_list` with it. |
n | integer | no | 1 | 1–9 | Images in a `single` job. Kling ignores it for a series, but it is still checked. |
series_amount | integer or string | no | 4 | 2–9 · auto | Images in a `series` job; `auto` lets Kling choose, at most 9. Kling ignores it for `single`, but it is still checked. |
aspect_ratio | string | no | auto | 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · auto | `auto` follows your pictures. Kling does not support `auto` for text-to-image (no `image_list`): name a ratio there. |
watermark_info | object | no | — | {"enabled": false} | Only `false` is accepted: a watermarked copy is not available on this gateway yet. |
Anything not listed here is refused rather than ignored, so a typo fails loudly instead of quietly producing something else.
Worked example
curl https://api.sociaro.com/v1/kling/generations \
-H "Authorization: Bearer $SOCIARO_API_KEY" -H "Content-Type: application/json" \
-d '{ "model": "kling/kling-v3-omni",
"prompt": "the cup from the reference picture on a marble counter, four times of day",
"image_list": [ { "image": "https://your-cdn.example.com/cup.png" } ],
"result_type": "series", "series_amount": 4, "resolution": "2k" }'
curl https://api.sociaro.com/v1/kling/generations/{job_id} -H "Authorization: Bearer $SOCIARO_API_KEY"Submit and poll. Send kling/kling-v3-omni to POST /v1/kling/generations and poll
GET /v1/kling/generations/{job_id}. It is not on the Jobs API (/v2).
The body is Kling's image body, flat: every field at the top level, beside model. Kling's model_name is set
by the gateway (kling-v3-omni): leave it out, or send that value; any other is a 400. Refused, each a 400
before anything is sent: callback_url (poll instead), external_task_id (the gateway sets its own),
element_list, watermark_info.enabled: true, and any other field Kling does not define. The body is capped at
1 MiB, so pictures go in as URLs.
What comes back. The finished poll carries media_url, the first image, and media_urls, every image in Kling's
order (present even for one image), each its own link for the hour: download them on the poll that hands them to
you. Kling's task_result keeps only result_type and each image's index; read our status, not Kling's
task_status.
How it is billed. Per image delivered, at Kling's list price: $0.028 an image at 1k or 2k, $0.056 at 4k.
You pay for the images the finished job hands you, never more than you asked for: n for single images,
series_amount for a series (auto counts as at most 9). Billed once, when the job completes; a failed job is not
billed. A series of four at 2k is $0.112 when all four are delivered. Kling counts one slot of its capacity per
image asked for, so a large n or series_amount can meet a 429 that a smaller job would not; the message, Kling's
own words when it gave them, adds a note saying so when that is the reason.
How a job runs
Generation takes longer than a request should wait, so it goes in three moves: submit, then poll, then collect.
# 1. submit — the model id plus the fields above
curl -sS https://api.sociaro.com/v1/alibaba/generations \
-H "Authorization: Bearer $SOCIARO_API_KEY" -H "Content-Type: application/json" \
-d '{ "model": "…", "prompt": "…" }'
# -> { "job_id": "<id>", "status": "submitted" }
# 2. poll every 3-5 s for images, 5-10 s for video
curl -sS https://api.sociaro.com/v1/alibaba/generations/<id> \
-H "Authorization: Bearer $SOCIARO_API_KEY"
# -> { "job_id": "…", "status": "processing" }
# -> { "job_id": "…", "status": "completed", "model": "…",
# "media_url": "https://api.sociaro.com/v1/media/<media_id>" }
# -> { "job_id": "…", "status": "failed", "model": "…", "error": { "code": …, "message": … } }
# 3. collect within the hour — the opaque id IS the credential, no header needed
curl -sSL "https://api.sociaro.com/v1/media/<media_id>" -o out.mp4
Use the job_id verbatim as the path segment when polling: the two names are the same value.
Which submit and poll URL this model uses is at the top of this page, under Calling it.
Reading the poll
status is one of processing · completed · failed. Only completed carries media_url,
only failed carries error.
Gate on status, never on the poll's HTTP code. A poll-time failure is HTTP 200 with
status: "failed" and an error object of { "code", "message" }, plus provider_code when the
generator supplied one — on every failure branch, including one where the result could not be
delivered. A submit-time rejection is different: it comes back as its own HTTP status with the
reason in the body.
code is ours and stable; message is the generator's. Match on code: it comes from a small
fixed set, and provider_failed still means what it always meant. A rejection of what you sent —
a size out of range, an unusable input — additionally sets code: "invalid_request", because that is
a different thing for your code to do. message now carries the generator's own sentence, and
provider_code its own code (OutputVideoSensitiveContentDetected.PolicyViolation,
IPInfringementSuspect), so a moderated generation, a copyright refusal and a broken renderer are
finally distinguishable. Treat provider_code as informational: the vendors change these strings
without telling us, so branch on ours.
message is variable text, capped at 400 characters. It used to be a single fixed
43-character sentence, so if you compare it by equality or keep it in a narrower column, that needs
changing — match on code, and on provider_code when you need the finer distinction.
Two things that text is not. It does not name the generator behind the model: the names of the
services and hosts that actually run your job are substituted out before you see it, so do not parse
it for one. What it does not hide is a name you already have — the halves of the model id you
called (alibaba, bytedance, wan, qwen, seedance, seedream, happyhorse) stay as written,
because blanking those would garble the message exactly where it is useful: Model
alibaba/wan-2-7-image not found has to survive intact. And the text can quote your own request
back: a moderation message often contains the fragment it objected to. That is why we do not write
it into our own logs, and why forwarding or storing a failed poll's message is your decision to
make rather than something to do by default.
Collecting the result
media_url points at our host, not the generator's. It is a capability: the opaque id is the
credential, so no Authorization header is needed and anyone holding the link can fetch it. It
expires within the hour — download rather than store the link.
Several images are not optional extras. An Alibaba image model asked for more than one picture
(n above 1) is charged for the number of pictures the generator reports making, and every link it
returns is delivered, never fewer than that number: media_urls lists
all of them in the generator's order (present on every image result, even a single one) and
media_url is the first. Each has its own link and its own expiry. If any one of them cannot be
delivered the job is reported failed and nothing is charged — unlike a still or a layer, an
image you paid for is never left out.
Rules the gateway adds
Two fields are ours and never reach the generator:
| Field | Notes |
|---|---|
model |
which model to run |
user |
your own end-user id. Recorded against this job's spend so you can attribute cost per end user, and stripped before the request leaves us, so the generator never sees it. Validated BEFORE the job is created, so a rejection is free: a string of at most 128 characters, no control characters, valid UTF-8. Omitting it, or sending null, is fine and simply records no end user |
An unknown field is always a 400. Most generators reject one themselves; some accept it,
ignore it, render something other than what you asked for and bill you — so we refuse it for you.
Either way you get 400 unknown field(s): [...] naming the offender, never a surprise render.
Ranges and enums are the generator's own and we do not re-validate most of them, so an
out-of-range value comes back as its rejection, in its wording and with its numbers. The one thing
we DO check ourselves is resolution, because an unsupported tier is silently ignored rather than
refused: you would ask for the higher tier, be handed a lower one, and be charged. The tiers on
this page are read from what the vendor prices, so they change when the vendor publishes one.
Authentication
Authorization: Bearer <your-api-key> on submit and on poll. The key must be valid AND granted
this model — 403 otherwise.
One deliberate exception on poll: a key that is over budget may still poll and collect a job it already submitted, so work you have already paid for is never stranded by a budget that ran out mid-generation. While the key is over budget the gateway cannot read its model list at all, so the per-model grant is not re-checked on those polls — a grant revoked after submit still collects that job. Ownership is always enforced: a job can only be polled by the key that created it, and submit is always refused in that state.