ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
ByteDance 字节豆包
Proprietary API ByteDance 字节豆包 · doubao-seed-2-1-turbo-260628 · Text+Image+Video

Doubao-Seed-2.1-Turbo (豆包极速) Official Specifications, Pricing & Benchmarks

High-throughput multimodal commercial Turbo model on Volcengine Ark with 256K context.

📋 Doubao-Seed-2.1-Turbo (豆包极速) Official API & System Card Specifications

Verified against official ByteDance 字节豆包 developer documentation & pricing

API Model ID: doubao-seed-2-1-turbo-260628

1. Identity & Capabilities

API Spec
API Model ID
doubao-seed-2-1-turbo-260628
Release Date
2026-06-23
Weight License
Proprietary (Undisclosed)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
256,000 tokens (256K)
Max Output Tokens
256,000 tokens
Input Modalities
Text + Image + Video
Output Modalities
Text
Direct China Access
✅ Direct CN + RMB
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

CNY / 1M
Input / 1M Tokens
¥ 3
Cached Input / 1M
¥ 0.6 -80%
Output / 1M Tokens
¥ 15
Tiered Pricing Notes
Ultra-high-QPS domestic workhorse starting at ¥0.3/1M input (¥0.06 cached)

🏆 Official Benchmark Results

Sourced from official System Card / Model Card & technical reports

Arena Elo ~1438 AA Index 42
📚 Knowledge
C-Eval 89.2 %

C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context.

📚 Knowledge
MMLU-Pro 81.4 %

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks.

🧠 Reasoning
GPQA Diamond 78 %

PhD-level Google-proof science reasoning questions

👁️ Multimodal
MMMU 76.5 %

MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning.

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Low-Latency Chat & Triage
temperature=0.7 top_p=0.9 max_tokens=16,384

Closest Self-Hostable Open-Weight Alternatives to Doubao-Seed-2.1-Turbo (豆包极速)

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Doubao-Seed-2.1-Turbo (豆包极速) open-source or proprietary?

Doubao-Seed-2.1-Turbo (豆包极速) (doubao-seed-2-1-turbo-260628) is a proprietary commercial model by ByteDance 字节豆包. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Doubao-Seed-2.1-Turbo (豆包极速)?

Doubao-Seed-2.1-Turbo (豆包极速) supports 256K input context and 256,000 max output tokens, priced at ¥3/1M input (¥0.6/1M cached) and ¥15/1M output.