ByteDance: Seed OSS 36B Instruct

bytedance/seed-oss-36b-instruct

131KContext Window

Online

Seed-OSS-36B-Instruct is a 36B-parameter instruction-tuned reasoning language model from ByteDance’s Seed team, released under Apache-2.0. The model is optimized for general instruction following with strong performance in reasoning, mathematics, coding, tool use/agentic workflows, and multilingual tasks, and is intended for international (i18n) use cases. It is not currently possible to control the reasoning effort.

Capabilities

🧠 ReasoningText GenerationCode GenerationAnalysis & Reasoningmodels.reasoning

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

Pricing

Pay per use, no monthly fees

Input Token< ¥0.001/1K Token

Output Token< ¥0.001/1K Token

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

response = client.chat.completions.create(
    model="bytedance/seed-oss-36b-instruct",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)

FAQ

ByteDance: Seed OSS 36B Instruct

bytedance/seed-oss-36b-instruct

In< ¥0.001/1K

Out< ¥0.001/1K

Context Window131K

Start Using →View Integration Docs

Related Models

View All → →

ByteDance: UI-TARS 7B

bytedance/ui-tars-1.5-7b

< ¥0.001/1K

ByteDance: Seedance 1.5 Pro (experimental)

bytedance/seedance-1-5-pro

< ¥0.001/1K

← ← Back to Models

Ready to get started?

Get 1M free tokens on registration, no monthly fees or minimum spend