4 models · image
Seedream API
Seedream is a family of AI image models made by ByteDance. varg runs 4 of them on one API key: Seedream 5 Pro, Seedream 5.0 Flash, Seedream 5 Lite and 1 more. Between them they cover text to image and image to image; they return images.
- Seedream 5 Pro
- From $0.0675/image
- Made by
- ByteDance
- Flagship id
seedream_5_pro
Every Seedream model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/image/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream_5_pro",
"prompt": "A ceramic teapot shaped like a sleeping fox, studio product shot, soft light"
}'Seedream models and prices
Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
Seedream 5 Proseedream_ | ByteDance Seedream 5 Pro. Text-to-image and image editing. | Text to image, Image to image | From $0.0675/image | ~25 s |
Seedream 5.0 Flashseedream_ | ByteDance Seedream 5.0 Flash. Fast, low-cost text-to-image and editing with up to 10 reference images, up to 2K. | Text to image, Image to image | $0.027/image | ~15 s |
Seedream 5 Liteseedream_ | ByteDance Seedream 5 Lite. Text-to-image. | Text to image | From $0.03 per runfrom $0.028/image | ~30 s |
SeedDream v4.5 Editseedream_ | ByteDance SeedDream. Image editing via text prompt. | Image to image | From $0.50 per run$0.50/image | ~15 s |
Call the Seedream API
The call below runs Seedream 5 Pro. For another Seedream model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/image/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
curl -X POST https://api.varg.ai/v2/tools/image/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream_5_pro",
"prompt": "A ceramic teapot shaped like a sleeping fox, studio product shot, soft light"
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs Seedream 5 Pro with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "image",
"input": {
"model": "seedream_5_pro",
"prompt": "A ceramic teapot shaped like a sleeping fox, studio product shot, soft light"
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool image '{"model":"seedream_5_pro","prompt":"A ceramic teapot shaped like a sleeping fox, studio product shot, soft light"}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
Seedream compared
Price, limits and inputs side by side, from the same catalog as this page.
How to use Seedream
Step-by-step pages on varg how to.
Seedream API: questions
- How much does the Seedream API cost on varg?
- Among the Seedream models with a stated run price, the lowest is from $0.03 per run (from $0.028/image), on Seedream 5 Lite. Seedream 5 Pro (from $0.0675/image) and Seedream 5.0 Flash ($0.027/image) are billed by rate with no stated minimum, so a short request can cost less. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which Seedream models are on varg?
- 4: Seedream 5 Pro (from $0.0675/image), Seedream 5.0 Flash ($0.027/image), Seedream 5 Lite (from $0.03 per run) and SeedDream v4.5 Edit (from $0.50 per run). Each has its own page with the parameters and a call to copy.
- Which Seedream models take an image?
- 3 of the 4: Seedream 5 Pro, Seedream 5.0 Flash and SeedDream v4.5 Edit. The catalog lists image to image for them; pass the image as a URL in "files".
- How long do Seedream requests take?
- Typically from about 15 s (Seedream 5.0 Flash) to about 30 s (Seedream 5 Lite), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the Seedream API?
- Send POST https://api.varg.ai/v2/tools/image/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "seedream_5_pro". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use Seedream from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "image" and the model id, for example "model": "seedream_5_pro".
More model APIs
Same API key, same request shape: change the model string to switch.
For AI agents: each model above has its full spec as Markdown at varg.ai/models/seedream_5_pro.md (swap the id), and every model is listed in varg.ai/models/llms.txt.