Seed 1.6

by ByteDance

Seed 1.6 is the flagship general-purpose model from ByteDance's Seed team, launched in June 2025 as part of the Doubao Seed line. It uses a sparse mixture-of-experts design with 230 billion total parameters, activating roughly 23 billion per forward pass, and pairs a 256K context window with text, image, and video understanding. Its signature feature is adaptive thinking, an approach that decides how much reasoning to spend based on how hard the prompt is, so simple queries stay fast while complex ones get deeper chains of thought. With tool calling and structured output on top, it suits agent backends, long-document analysis, and multimodal reasoning tasks that mix screenshots or video frames with text.

Key info

Input
Output
Features
Context window
262K
Max output
33K
Input price
$0.25 /1M
Output price
$2.00 /1M
  • No training by default
  • GDPR DPA available

Available routes

Seed 1.6 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 retentionTrainingInputOutput
MultiNot by defaultNo$0.25$2.00

Data handling per route

Each route hosting Seed 1.6 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 Seed 1.6 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/seed-1.6",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Seed 1.6 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