Image generation with Seedream 5.5 (Beta), ByteDance's newest Seedream image model: one model for text-to-image, edits and multi-image fusion, as an async job. Submitting returns a job id at once (HTTP 202), then you poll the result or let a webhook push it. 1K and 2K in 9 ratios, the original PNG delivered; billed per image, nothing charged on failure. During the Beta a request may fail or slow down at peak times; resubmit it as is.
Try in Playground →Quick start
Three steps: submit a job, poll it, take the image link. Replace YOUR_API_KEY with your key and the commands below run as they are.
Step 1 · Submit (returns a job id at once, HTTP 202)
curl https://kovapi.com/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "seedream-5.5", "prompt": "A cafe doorway in an old alley at dusk, a chalkboard reading “Today: Osmanthus Latte $4”, a ginger cat beside it, photorealistic", "size": "16:9", "resolution": "2K"}'Response (HTTP 202)
{
"id": "img_7f3c9a1e2b4d6f8a0c1e3b5d",
"object": "image.generation.job",
"status": "queued",
"created": 1791281400,
"model": "seedream-5.5"
}Step 2 · Poll every 2–3 seconds until status is succeeded or failed
curl https://kovapi.com/v1/images/jobs/img_7f3c9a1e2b4d6f8a0c1e3b5d \ -H "Authorization: Bearer YOUR_API_KEY"
Response when it succeeds
{
"id": "img_7f3c9a1e2b4d6f8a0c1e3b5d",
"object": "image.generation.job",
"status": "succeeded",
"created": 1791281400,
"model": "seedream-5.5",
"data": [
{"url": "https://img.kovapi.com/i/2be8cd16d37f3a4b9c0e1f2a3b4c5d6e.png"}
],
"usage": {"images": 1, "resolution": "2K", "model": "seedream-5.5"}
}Step 3 · data[0].url is the image (the original PNG). It is kept for 7 days; download it to your own storage to keep it longer.
Complete example (Python: submit, wait, save to disk)
import time
import requests
BASE = "https://kovapi.com/v1"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY"}
# 1. submit
job = requests.post(f"{BASE}/images/generations", headers=HEADERS, json={
"model": "seedream-5.5",
"prompt": "A cafe doorway in an old alley at dusk, a chalkboard reading “Today: Osmanthus Latte $4”, a ginger cat beside it, photorealistic",
"size": "16:9",
"resolution": "2K",
}).json()
if "error" in job:
raise SystemExit(job["error"]["message"])
# 2. poll every 3 seconds until it finishes
while job["status"] not in ("succeeded", "failed"):
time.sleep(3)
job = requests.get(f"{BASE}/images/jobs/{job['id']}", headers=HEADERS).json()
# 3. download the image
if job["status"] == "succeeded":
url = job["data"][0]["url"]
with open("seedream-5.5.png", "wb") as f:
f.write(requests.get(url).content)
print("saved", url)
else:
print("failed:", job["error"]["code"], job["error"]["message"])Authentication
Authorization: Bearer YOUR_API_KEY Content-Type: application/json
Create an API Key in the console to start.
Request parameters
The JSON body of POST /v1/images/generations:
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | The model id: seedream-5.5. |
| prompt | string | Yes | What to draw. For image-to-image, say what to change. |
| size | string | No | Aspect ratio: 1:1 (default), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21. A pixel size (e.g. 2560x1440) also works and is matched to one of these 9 by its ratio; any other ratio returns 400 at submit, nothing charged. You get that ratio's native size (see the size table in the docs). |
| resolution | string | No | Tier: 1K (default) or 2K. There is no 4K. |
| image / images | string / array | No | Reference images; sending any makes it an edit or a fusion: one in image, several in images (up to 10). Each can be a public image URL, a data: URI or base64. With several, say in the prompt what each one is for, in order, e.g. "the person from image 1 sitting in the cafe from image 2". |
| n | integer | No | Always 1: one image per request. For several, submit several jobs at once; any other value returns 400 at submit, nothing charged. |
| callback_url | string | No | Where to push the result when the job ends; see Webhooks below. |
Other OpenAI parameters (quality, background, output_format, style and the like) are not supported: they have no effect and do not change the price. Results are always the original PNG, returned as a url; with response_format: "b64_json" the result also carries a base64 copy.
Price
Billed per image by tier only: aspect ratio, text-to-image or image-to-image make no difference. The tier price is held when you submit and refunded in full if the job fails. 1 credit = $0.005.
| Tier | Credits per image | USD per image |
|---|---|---|
| 1K | 4 | $0.02 |
| 2K | 6 | $0.03 |
Aspect ratio, resolution and output size
Put the ratio in size and the tier in resolution. You get the original the model draws at that ratio, at one fixed size per ratio and tier, as listed below; never cropped or resized.
| Aspect ratio | 1K | 2K |
|---|---|---|
| 1:1 | 1024x1024 | 2048x2048 |
| 16:9 | 1424x800 | 2816x1584 |
| 9:16 | 800x1424 | 1584x2816 |
| 4:3 | 1152x864 | 2368x1776 |
| 3:4 | 864x1152 | 1776x2368 |
| 3:2 | 1248x832 | 2496x1664 |
| 2:3 | 832x1248 | 1664x2496 |
| 21:9 | 1568x672 | 3136x1344 |
| 9:21 | 672x1568 | 1344x3136 |
- Only the 9 ratios in the table are supported; any other (5:4, 2:1 ...) returns 400
unsupported_sizeat submit and nothing is charged. A few native sizes are slightly off the nominal ratio (1K 16:9 is 1424×800): that is the size the model itself draws. Before delivery the ratio, the size and the model named in the C2PA credential are checked; if any of them does not match, the image is not delivered, the job fails and nothing is charged. sizecan also be a pixel size (e.g.2560x1440): it only sets the ratio (within 1.5% of one of the 9), and you still get the original at that ratio's size in the table. The tier comes fromresolution; without it the longest side decides: up to 1600 is 1K, 1601 to 3200 is 2K.- This model has 1K and 2K only: asking for 4K (
resolution: "4K", or asizewhose longest side is over 3200) is refused at once with 400unsupported_resolution, and nothing is charged. For 2K, sendresolution: "2K".
Image-to-image and reference images
- Send
image(one picture) orimages(several, up to 8; any beyond 8 are not used) and the job runs image-to-image; say in the prompt what to change.POST /v1/images/editstakes the same parameters. - Both endpoints take a JSON body only, not a multipart file upload, so the OpenAI SDK's
images.edit()cannot be used as is: pass links or base64 as in the example below. - Each reference can be a public image URL (http or https), a data: URI or plain base64, up to 16MB each, in a common format such as JPEG, PNG or WebP.
- A URL has to download the image itself: not a web page, and not behind a login or hotlink protection. A reference we cannot read is refused at submit with a 400 that says which one and why; no job is created and nothing is charged.
- For edits and fusions the output ratio follows
size(1:1 when absent), not the reference image; to keep the original's ratio, setsizeto that ratio. You get the model's original, never cropped or resized. To edit over several rounds, pass the previous result as the next round's reference. - We host the references for you and keep them for 7 days.
Image-to-image with two references
curl https://kovapi.com/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "seedream-5.5", "prompt": "Keep the people, change the background to a beach at night with warm string lights", "images": ["https://example.com/people.jpg", "https://example.com/beach.jpg"], "size": "3:4", "resolution": "2K"}'Job status and fields
GET /v1/images/jobs/{id} reports these statuses; every field is described in Async jobs. Poll every 2–3 seconds, or use a webhook.
| Status | Meaning |
|---|---|
| queued | Waiting in line. Carries queue_position (jobs ahead of yours) and eta_seconds (expected wait). |
| processing | Rendering. |
| succeeded | Done. The result is in data[0].url, the billing detail in usage. |
| failed | Failed. The reason is in error; the credits held for the job are refunded in full. |
One account runs up to 50 jobs at a time; further jobs wait in submission order, and a job that has not started after 15 minutes fails and is refunded in full. Job records are kept for 3 days and image links for 7 days.
How long it takes
Usually 20–40 seconds from submit to result when the service is not busy; 2K and several references are a little slower. During the Beta, peaks can be slower or fail (failures are not charged).
Errors and refunds
An error at submit comes back at once as HTTP 4xx / 5xx: no job is created and nothing is charged. A failure after the job was accepted is reported by the job endpoint, and the hold is refunded in full. Every code is listed under Error codes.
Errors at submit
| HTTP | code | Cause | What to do |
|---|---|---|---|
| 400 | missing_prompt | /v1/images/generations has no prompt. | Add a prompt. |
| 400 | invalid_request | A reference image cannot be read (dead link, not an image, over 16MB...; message says which one and why), /v1/images/edits has no reference image, the body is not a JSON object, or n is not an integer. | Fix what message says and submit again. |
| 400 | unsupported_resolution | The model does not offer the chosen resolution tier (Grok image generation has no 4K, for example). | Pick another tier; each model's doc lists its tiers. |
| 400 | model_not_found | The model id is misspelled, model is missing, or the model cannot be used on this endpoint (a chat model on the image endpoint, for example). | Use a model id from GET /v1/models or the API reference. |
| 401 | invalid_api_key | The key does not exist, was deleted or is disabled, or the account is disabled. | Check the key on the API Keys page of the console. |
| 402 | insufficient_quota | Not enough balance to hold this request. The gateway holds the highest possible cost of the request first, so a burst of concurrent calls can trigger it too. | After a burst, wait a few seconds and retry; otherwise top up. |
| 429 | rate_limit_exceeded | Over the requests-per-minute limit set on this key (counted over the last 60 seconds). No Retry-After header. | Wait a few seconds and retry, or raise the key's limit in the console. |
| 503 | model_maintenance | The model is under maintenance and takes no requests; no other model answers in its place meanwhile. | Retry when maintenance ends; see Status. |
| 503 | service_unavailable | A temporary failure on our side, such as storing a reference file; /v1/responses also answers 503, with Retry-After, when it cannot take requests for a moment. | Retry shortly. |
Failed jobs (status failed)
| code | When you see it | What to do |
|---|---|---|
| moderation_blocked | Image: the model provider's safety system refused the prompt or a reference image (the code may also be content_policy_violation). | Rewrite the prompt or replace the reference; resubmitting it unchanged is usually refused again. |
| upstream_error | Any other failure: the automatic retries did not help, the job waited 15 minutes without starting, the upstream refused without a reason, and so on; message says which. | Submitting again usually works. |
Webhooks instead of polling
Add callback_url when you submit and the moment the job ends, success or failure, the gateway pushes exactly what the poll endpoint returns to that URL, signed and retried on failure. You can also set an account-wide address under Settings → Webhook in the console. Webhook docs →
curl https://kovapi.com/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "seedream-5.5", "prompt": "A cafe doorway in an old alley at dusk, a chalkboard reading “Today: Osmanthus Latte $4”, a ginger cat beside it, photorealistic", "size": "1:1", "callback_url": "https://your-domain.com/webhook"}'