doubao · Balanced
ByteDance Seed 2.0 Code
ByteDance Seed 2.0 Code is a multimodal model optimized for agentic coding, frontend development, multilingual programming, long-running tool workflows, and coding agents. It supports image and video input, a 262k context window, and up to 131k output tokens.
- Reasoning
- Tools
- Vision
- Structured output
- Video input
- Input
- Text, Images, Video
- Output
- Text
- Reasoning effort
- none · low · medium · high
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $0.50
- Output
- $3.00
Reference prices as published by the model provider. API example
Specifications
- Context window
- 262.1K
- Max output
- 131.1K
- Average output (7 days)
- 113 tokens
- Longer than 10% of 468 models
Side by side
ByteDance Seed 2.0 Code compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| ByteDance Seed 2.0 CodedoubaoThis model | GPT-3.5 TurboOpenAIRemove | |
|---|---|---|
| Provider | doubao | OpenAI |
| Discovery tier | Balanced | Balanced |
| Added | Aug 11, 2026 | Jan 1, 2024 |
| Limits | ||
| Context window | 262.14KBest | 16.39K |
| Max output | 131.07KBest | 4.1K |
| Average output | 113 tokens | — |
| Pricing, USD per 1M tokens | ||
| Input | $0.50 | $0.50 |
| Output | $3.00 | $1.50Best |
| Benchmark indexes | ||
| Intelligence Index | — | 5.5 |
| Coding Index | — | 10.7 |
| Capabilities | ||
| Reasoning | Yes | No |
| Tools | Yes | No |
| Vision | Yes | No |
| Structured output | Yes | No |
| Video input | Yes | No |
| Reasoning effort | none, low, medium, high | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- ByteDance Seed 2.0 Code
- GPT-3.5 Turbo
Intelligence Index
- ByteDance Seed 2.0 Code—
- GPT-3.5 Turbo5.5
Indexes
Coding Index
Composite of the coding evaluations
- ByteDance Seed 2.0 Code: —
- GPT-3.5 Turbo: 10.7
Reasoning and knowledge
GPQA Diamond
Graduate-level science questions
- ByteDance Seed 2.0 Code: —
- GPT-3.5 Turbo: 29.7%
MMLU-Pro
Multi-subject knowledge and reasoning
- ByteDance Seed 2.0 Code: —
- GPT-3.5 Turbo: 46.2%
Math
MATH-500
Competition math problems
- ByteDance Seed 2.0 Code: —
- GPT-3.5 Turbo: 44.1%
Scores from Artificial Analysis, updated Oct 26, 2026.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "bytedance-seed/seed-2.0-code",
"reasoning_effort": "medium",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="bytedance-seed/seed-2.0-code",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)doubao
Related models
Other doubao models, starting with the same family.