Seed 2.0 Code API

About Seed 2.0 Code

Coding-tuned 256K-context model with strong front-end results and multilingual programming support for AI coding tools and agents.

Also known as Seed Code, ByteDance Seed 2.0 Code, Seed-2.0-Code, seed-2-0-code

Seed 2.0 Code specs

Model ID

seed-2-0-code

Provider

ByteDance

Category

Text Generation

Released

Feb 14, 2026

Context window

256K tokens

Max output

128,000 tokens

Input

TextImageVideoDocument

Output

Text

Structured output

Not supported

Region

Malaysia

Endpoints

POST/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/seed-2-0-code:generateContent

Alternate model IDs

bytedance/seed-2-codedola-seed-2.0-codedoubao-seed-2-codeseed-2-0-code-preview-260328seed-2-code

Seed 2.0 Code API pricing

Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.

How to call the Seed 2.0 Code API

Seed 2.0 Code serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id seed-2-0-code. Get an API key from the EmpirioLabs dashboard.

curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seed-2-0-code",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'

from openai import OpenAI

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

response = client.chat.completions.create(
    model="seed-2-0-code",
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)

Seed 2.0 Code API parameters

Request parameters supported by the Seed 2.0 Code API on EmpirioLabs. Defaults apply when a field is omitted.

Good to know

Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.

Per-tool billing (usage.tool_usage)

When this model invokes built-in tools (web search, code interpreter, etc.) inside a single request, the response carries a normalized usage.tool_usage map alongside the token counts. The example below shows the shape — exact field names, units, and which tools appear can vary slightly per provider:

"usage": {
  "prompt_tokens": 123,
  "completion_tokens": 456,
  "cost_usd": 0.0042,
  "tool_usage": {"web_search": 3, "code_interpreter": 1}
}

The tool counts are already factored into cost_usd — they are surfaced for transparency so you can audit per-tool billing. The field is omitted when no tools were invoked.

Seed 2.0 Code API: common questions

How much does the Seed 2.0 Code API cost?

On EmpirioLabs, Seed 2.0 Code is billed pay as you go. The live rate card on this page always matches what the API charges.

What is the context window of Seed 2.0 Code?

Seed 2.0 Code supports a 256K-token context window with up to 128,000 output tokens per response.

Is the Seed 2.0 Code API OpenAI-compatible?

Yes. Seed 2.0 Code serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to seed-2-0-code.

Can I try Seed 2.0 Code in the browser before integrating?

Yes. The EmpirioLabs playground runs Seed 2.0 Code in the browser with the same parameters the API exposes, so you can test prompts before writing code.

How do I get a Seed 2.0 Code API key?

Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.