Seedream 4.5

by ByteDance

Seedream 4.5 is ByteDance's high-fidelity image model from December 2025, an upgrade over September's Seedream 4.0 that unifies generation and editing in one architecture while running roughly ten times faster than its predecessor. It renders text within images precisely and outputs at up to 4K resolution. The model accepts as many as 10 reference images per request, blending styles, characters, or products while holding subject fidelity, perspective, and lighting steady. That makes it a workhorse for e-commerce compositing, brand asset variations, and instruction-driven edits where the result has to stay consistent with source material.

Key info

Input
Output
Features
Pricing
$0.04 / generation
Billing
Per generation
  • No training by default
  • GDPR DPA available

Pricing

Usage-based pricing, billed per generation, not by token.

VariantPrice
Standard$0.04 / generation

Available routes

Seedream 4.5 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.

ProviderRegionZero data retentionTrainingPrice
MultiNot by defaultNo$0.04 / generation

Data handling per route

Each route hosting Seedream 4.5 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

BytePlus Multi-region

Zero data retention is not on by default — abuse monitoring, 180-day retention. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
Not by default — abuse monitoring, 180-day retention. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring (180-day retention)
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
GDPR DPA
DPA available
Transfer mechanism
SCCs

Get started

Call Seedream 4.5 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "bytedance:ap/seedream-4.5",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Seedream 4.5 with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from ByteDance

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation