Seedream 5.0 API: Pro, Lite and Flash compared, with code
Seedream 5.0 comes in three tiers, and the names do not say which one makes the biggest pictures. This guide lays out what each Seedream model in the catalogue does, what it costs per image and how to call it, including multi-reference edits.
The Seedream models on one API
Seedream is ByteDance's image family. Every version in the catalogue makes images from a prompt and edits images you send, and they all take the same request on Revana. The 5.0 generation splits into three tiers, and the older 4.5 and 4.0 are still there for teams that tuned prompts on them:
| Model | Model id | Sizes | Reference images | Price from | Routes |
|---|---|---|---|---|---|
| Seedream 5.0 Pro | seedream-5.0-pro | 1K, 1.5K, 2K | up to 10 | $0.04 / image | three routes |
| Seedream 5.0 Lite | seedream-5.0-lite | 2K, 3K, 4K | up to 6 | $0.03 / image | three routes |
| Seedream 5.0 Flash | seedream-5.0-flash | 1K, 1.5K, 2K | up to 10 | $0.02 / image | two routes |
| Seedream 4.5 | seedream-4.5 | 2K, 4K | one image | $0.04 / image | two routes |
| Seedream 4.0 | seedream-4.0 | 1K, 2K, 4K | one image | $0.03 / image | two routes |
The naming can mislead. "Lite" in Seedream 5.0 does not mean small pictures: Lite is the tier that goes up to 4K, while Pro tops out at 2K. Pro and Flash take more reference images (10, against 6 for Lite), which matters for edits that combine a product, a model and a setting.
Which Seedream to use
- Seedream 5.0 Pro for the best 5.0 results at up to 2K and edits with many references. The price is flat across sizes, so ask for 2K.
- Seedream 5.0 Lite when you need 3K or 4K output from the 5.0 generation, for print, large screens or heavy cropping.
- Seedream 5.0 Flash for high volume: drafts, variants and catalogue images at $0.02 each.
- Seedream 4.5 if your prompts are already tuned on it. It is known for sharp 2K and 4K output and strong typography.
We do not publish quality scores. Run the same handful of prompts on Pro, Lite and Flash and look at the results; at these prices the test costs a few cents.
Seedream pricing (October 2026)
Every Seedream model is billed once per image. The table shows each size and what 100 and 1,000 images cost.
| Model | Size | Per image | 100 images | 1,000 images |
|---|---|---|---|---|
| Seedream 5.0 Pro | 1K to 2K | $0.04 | $4.00 | $40.00 |
| Seedream 5.0 Lite | 2K | $0.03 | $3.00 | $30.00 |
| Seedream 5.0 Lite | 3K | $0.03 | $3.00 | $30.00 |
| Seedream 5.0 Lite | 4K | $0.04 | $4.00 | $40.00 |
| Seedream 5.0 Flash | 1K to 2K | $0.02 | $2.00 | $20.00 |
| Seedream 4.5 | 2K or 4K | $0.04 | $4.00 | $40.00 |
| Seedream 4.0 | 1K to 4K | $0.03 | $3.00 | $30.00 |
The router sends each job to the cheapest route that can run it and falls back to the next if that route fails. You are charged the listed price once, only when the image is delivered. Seedream 5.0 Pro and Lite each have three routes, which helps when one route is busy. For how Seedream compares with other image models on price, see the cheapest image API guide.
Generate a Seedream 5.0 image
Send POST /v1/generations with the model id and an input, then poll the generation until it has succeeded or failed. This 2K Seedream 5.0 Pro image costs $0.04.
export REVANA_API_KEY="sr_live_..."
# 1. Submit the job (returns 202 with the generation id)
curl https://api.revana.si/v1/generations \
-H "Authorization: Bearer $REVANA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5.0-pro",
"input": {
"prompt": "An editorial photo of a ceramic teapot on a linen tablecloth, soft window light, shallow depth of field, muted sage and cream palette.",
"resolution": "2K",
"aspect_ratio": "3:2"
},
"max_cost_usd": 0.1
}'
# 2. Poll with the id from step 1 until status is "succeeded" or "failed"
curl https://api.revana.si/v1/generations/gen_01JC2V8K5T \
-H "Authorization: Bearer $REVANA_API_KEY"import os
import time
import requests
API = "https://api.revana.si/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['REVANA_API_KEY']}"}
resp = requests.post(f"{API}/generations", headers=HEADERS, json={
"model": "seedream-5.0-pro",
"input": {
"prompt": "An editorial photo of a ceramic teapot on a linen tablecloth, soft window light, shallow depth of field, muted sage and cream palette.",
"resolution": "2K",
"aspect_ratio": "3:2",
},
"max_cost_usd": 0.1,
})
resp.raise_for_status()
job = resp.json()
while job["status"] in ("queued", "running"):
time.sleep(3)
job = requests.get(f"{API}/generations/{job['id']}", headers=HEADERS).json()
if job["status"] == "succeeded":
print(job["output"]["urls"], job["cost_usd"])
else:
print("Failed:", job["error"])// Node 18 or later. Save as generate.mjs and run: node generate.mjs
const API = "https://api.revana.si/v1";
const headers = {
Authorization: `Bearer ${process.env.REVANA_API_KEY}`,
"Content-Type": "application/json",
};
const res = await fetch(`${API}/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "seedream-5.0-pro",
input: {
prompt: "An editorial photo of a ceramic teapot on a linen tablecloth, soft window light, shallow depth of field, muted sage and cream palette.",
resolution: "2K",
aspect_ratio: "3:2",
},
max_cost_usd: 0.1,
}),
});
if (!res.ok) throw new Error(`${res.status} ${await res.text()}`);
let job = await res.json();
while (job.status === "queued" || job.status === "running") {
await new Promise((r) => setTimeout(r, 3000));
job = await (await fetch(`${API}/generations/${job.id}`, { headers })).json();
}
if (job.status === "succeeded") console.log(job.output.urls, job.cost_usd);
else console.error("Failed:", job.error);{
"id": "gen_01JC2V8K5T",
"model": "seedream-5.0-pro",
"status": "succeeded",
"output": {
"urls": [
"https://cdn.revana.si/g/gen_01JC2V8K5T/0.png"
]
},
"cost_usd": 0.04,
"attempts": 1,
"error": null,
"created_at": "2026-10-28T10:14:02Z",
"completed_at": "2026-10-28T10:15:31Z"
}Edit with several references
Send up to 10 pictures to Seedream 5.0 Pro or Flash (6 to Lite) in image_urls, and say in the prompt what to take from each. If your files are local, upload them first with POST /v1/uploads; the link it returns is good for 14 days. This 4K edit on Seedream 5.0 Lite costs $0.04:
{
"model": "seedream-5.0-lite",
"input": {
"prompt": "Put the handbag from the first image on the marble shelf from the second image. Keep the logo and stitching exactly as they are. Warm boutique lighting.",
"image_urls": [
"https://example.com/handbag.png",
"https://example.com/shelf.jpg"
],
"resolution": "4K",
"aspect_ratio": "4:5"
},
"max_cost_usd": 0.1
}Sizes are model by model: Seedream 5.0 Pro refuses 4K and Lite refuses 1K. A size the model does not list comes back straight away as 422 invalid_input, with the sizes it does take, and nothing is charged.
See every Seedream version on the models page, the request reference in the docs and credit packs on the pricing page, or get an API key.
Frequently asked questions
How much does the Seedream 5.0 API cost?
In October 2026, Seedream 5.0 Pro costs $0.04 per image at 1K, 1.5K or 2K. Seedream 5.0 Lite costs $0.03 at 2K and 3K and $0.04 at 4K. Seedream 5.0 Flash costs $0.02 per image.
What is the difference between Seedream 5.0 Pro, Lite and Flash?
Pro goes up to 2K and takes up to 10 reference images. Lite goes up to 4K and takes up to 6. Flash goes up to 2K, takes up to 10 and has the lowest price of the three.
Does Seedream 5.0 support 4K?
Seedream 5.0 Lite does, at 2K, 3K and 4K. Seedream 5.0 Pro and Flash stop at 2K. Seedream 4.5 and 4.0 also offer 4K.
Can Seedream edit images?
Yes. Every Seedream model in the catalogue edits images: send them in image_urls (or image_url for one) with a prompt describing the result.
Is Seedream 4.5 still available?
Yes, as seedream-4.5 at $0.04 per image, in 2K or 4K. Seedream 4.0 is also available.
Am I charged for a failed Seedream image?
No. The price is held at submit and released if the job fails. You pay only for delivered images.
Try Seedream 5.0 with one key
One API key for every Seedream version and every other image and video model. Prepaid credit from $10, charged only for images that are delivered.