Call seedream-5.0-pro on Lazu for $0.045+ / image.
Seedream 5.0 Pro by ByteDance. Image generation and reference editing. Layer decomposition supported; billing uses actual output pixels and successful image count.
Prices and lanes
USD per million tokens. Availability covers the last 7 days, 2 hours per bar.
- Each successful output ≤ 2610000 px
- $0.045
- > 2610000 px
- $0.09
- Each layer, including base ≤ 2610000 px
- $0.0225
- Each layer, including base > 2610000 px
- $0.045
- Reference images
- 1 free; +$0.003 / additional image
Prices checked 2026-11-03 19:03 UTC · How to choose a lane · seedream-5.0-pro.json · seedream-5.0-pro.md
Capabilities
Example request
curl -X POST https://api.lazu.ai/v1/chat/completions \
-H "Authorization: Bearer $LAZU_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-5.0-pro",
"messages": [{ "role": "user", "content": "Hello from Lazu" }]
}'
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.lazu.ai/v1",
api_key=os.getenv("LAZU_API_KEY"),
)
resp = client.chat.completions.create(
model="seedream-5.0-pro",
messages=[{"role": "user", "content": "Hello from Lazu"}],
)
print(resp.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.lazu.ai/v1",
apiKey: process.env.LAZU_API_KEY,
});
const resp = await client.chat.completions.create({
model: "seedream-5.0-pro",
messages: [{ role: "user", content: "Hello from Lazu" }],
});
console.log(resp.choices[0].message.content);
Any OpenAI SDK works too: set base_url to https://api.lazu.ai/v1. Full integration docs
Questions
What is the difference between the stable and agent lanes?
The stable lane runs on each maker's official API, is billed at the list price, has the highest availability and suits every use. The agent lane runs on third-party subscription pools that serve the model through its official client, not the official API. It costs far less, but availability varies, a failed request does not fall back to the stable lane, and the pool adds its own preset context. So use it only inside the matching agent tool: Claude models in Claude Code, GPT models in Codex, Gemini models in Antigravity. For your own code, or anywhere the output must be controlled exactly, use the stable lane. Both lanes work with the same key, and each key picks the lane per model.
Can I call seedream-5.0-pro with the OpenAI SDK?
Yes. Point the SDK's base URL at https://api.lazu.ai/v1 and use seedream-5.0-pro as the model name.
How is it billed?
Per token actually used — input, output and cache — deducted from your wallet balance. There is no monthly fee, and every request shows up itemized in your usage log.