doubao · Balanced
Doubao Seed 2.1 Turbo
Fast, lower-cost model in the Doubao Seed 2.1 family for everyday chat, coding assistance, document work, and high-throughput productivity tasks. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.
- Input
- Text
- Output
- Text
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $0.50
- Output
- $2.50
Reference prices as published by the model provider. API example
Specifications
- Context window
- 256K
- Max output
- 128K
Side by side
Doubao Seed 2.1 Turbo compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Doubao Seed 2.1 TurbodoubaoThis model | MiniMax M1 80KMiniMaxRemove | |
|---|---|---|
| Provider | doubao | MiniMax |
| Discovery tier | Balanced | Balanced |
| Added | Jun 23, 2026 | Jan 8, 2025 |
| Limits | ||
| Context window | 256K | 1MBest |
| Max output | 128K | 131.07KBest |
| Pricing, USD per 1M tokens | ||
| Input | $0.50Best | $0.61 |
| Output | $2.50 | $2.42Best |
| Benchmark indexes | ||
| Intelligence Index | — | 11.7 |
| Math Index | — | 61.0 |
| Capabilities | ||
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Doubao Seed 2.1 Turbo
- MiniMax M1 80K
Intelligence Index
- Doubao Seed 2.1 Turbo—
- MiniMax M1 80K11.7
Indexes
Math Index
Composite of the math evaluations
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 61.0
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 57.7%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 8.9%
GPQA Diamond
Graduate-level science questions
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 69.7%
MMLU-Pro
Multi-subject knowledge and reasoning
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 81.6%
IFBench
Following precise output instructions
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 41.8%
Coding
LiveCodeBench
Recent competitive programming problems
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 71.1%
Math
AIME 2025
Competition mathematics, 2025 problems
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 61.0%
AIME
Competition mathematics
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 84.7%
MATH-500
Competition math problems
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 98.0%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 3.0%
τ²-Bench Telecom
Tool use in a customer-support simulation
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 34.2%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Doubao Seed 2.1 Turbo: —
- MiniMax M1 80K: 57.7%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 0.0%
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
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/doubao-seed-2.1-turbo",
"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/doubao-seed-2.1-turbo",
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.