Seed 1.8 is ByteDance's generalized agentic model that unifies perception, reasoning, and action in a single foundation. It combines text and image input with native search, code, and graphical user interface agent capabilities, enabling end-to-end task automation across information retrieval, GUI navigation, code execution, and multi-step workflows. The model is built for agentic reasoning and scores 67.6 on BrowseComp-en, where ByteDance reports it surpassing other leading models on this web-browsing benchmark. It supports three adaptive thinking modes that automatically adjust processing based on task complexity, balancing reasoning depth with inference efficiency. Seed 1.8 also delivers strong long-video understanding, scoring 87.8 on VideoMME. With a 256k context window and unified agent capabilities, Seed 1.8 targets real-world applications that need autonomous decision-making, iterative task completion, and grounded reasoning across multiple modalities and tool types.
Seed 1.8 runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| DeepInfra | US | Enterprise | No | $0.25 | $2.00 |
Training posture across routes: No training on prompts by default.
Each route hosting Seed 1.8 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.
Call Seed 1.8 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.
Copy this and paste it into your coding agent — Claude Code, Cursor, Codex, and more — and it'll wire up Opper for you.
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: "deepinfra/ByteDance/Seed-1.8",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
