Doubao-Seed-2.0-pro

doubao-seed-2-0-pro-260215

Get API keyAPI reference

Flagship all-purpose general model, designed for complex reasoning and long-chain task execution scenarios in the Agent era. Emphasizes multimodal understanding, long-context reasoning, structured generation, and tool-augmented execution. Outstanding capability in following complex instructions and satisfying multiple constraints, reliably handling multi-step complex planning, complex image-text reasoning, video content understanding, and high-difficulty analysis scenarios.

Context window1.0M

Provider豆包

Released2026/04/27

Playground

Pricing

The same model is available through multiple service channels — choose based on latency, reliability and cost.

Prices in $ / 1M tokens

To pick a channel, add a provider field to the request body, for example "provider": { "channel": "direct" }. Valid values are direct / stable / economical; omit it to use the default channel.

Direct

Direct upstream connection — best when you need native behavior and the full context window.

Input context	Input	Output	Cache read
≤ 32K	0.47/M	2.35/M	0.09/M
32K – 128K	0.71/M	3.53/M	0.14/M
> 128K	1.41/M	7.06/M	0.28/M

Overview

Input

Text Image

Output

Text

Doubao-Seed-2.0-pro API: The Flagship General-Purpose Model for the Agent Era

Doubao-Seed-2.0-pro is the flagship general-purpose model of ByteDance's Doubao large model family, designed for complex reasoning and long-chain task execution scenarios in the Agent era. It emphasizes multimodal understanding, long-context reasoning, structured generation, and tool-augmented execution.

This model stands out especially in complex instruction following and multi-constraint execution, capable of reliably handling scenarios such as multi-step complex planning, complex image-text reasoning, video content understanding, and high-difficulty analysis. With a 1M token context window, it is a suitable choice for enterprise-grade complex business scenarios.

SeaWhale AI provides Doubao-Seed-2.0-pro through an OpenAI-compatible interface, supporting multimodal input, tool calling, and streaming output.

Get API Key · Model ID: doubao-seed-2-0-pro-260215

---

Why Choose Doubao-Seed-2.0-pro

• Doubao Family Flagship General-Purpose Model — Designed for complex tasks in the Agent era
• Complex Instruction Following and Multi-Constraint Execution — Simultaneously satisfies multiple mutually constraining requirements
• 1M Token Context — Ample context space for long-chain tasks
• Multimodal Understanding — Unified processing of text and image inputs, with support for video content understanding
• Tool-Augmented Execution — Natively optimized for agent workflows
• Tiered Pricing — Billed in three tiers by input length; shorter inputs are cheaper

---

Core Capabilities

01 Complex Reasoning and Long-Chain Execution

Doubao-Seed-2.0-pro's core positioning is "complex reasoning for the Agent era." It can break down multi-step plans, track state across long chains, and handle branches and exceptions during execution.

• Multi-step complex planning and decomposition
• State tracking for long-chain tasks
• Handling of exceptional branches

02 Complex Instructions and Multi-Constraint Execution

When a task has multiple mutually constraining requirements at the same time (format, length, standards, factual constraints), the Pro version's multi-constraint execution capability is especially evident.

• Satisfying multiple constraints simultaneously
• Strict format and standards control
• Implementation of complex business rules

03 Image-Text and Video Understanding

Supports complex image-text reasoning and video content understanding, and can handle analytical tasks that require cross-modal association.

• Complex chart and document reasoning
• Video content understanding and extraction
• Analysis of mixed image-text materials

04 Structured Generation

In scenarios that require strictly structured output (JSON, tables, reports), the Pro version demonstrates strong stability and accuracy.

• Structured JSON output
• Table and report generation
• Data format conversion

---

Best Use Cases

Scenario	Description
Complex Agent tasks	Multi-step planning and autonomous long-chain execution
High-difficulty analysis	Business and data analysis requiring complex reasoning
Image-text and video understanding	Cross-modal content analysis and extraction
Multi-constraint content generation	Simultaneously meeting format, standards, and factual requirements
Enterprise-grade automation	Process implementation of complex business rules
Long-context processing	Large-scale materials within a 1M token window

---

Differences Between Doubao-Seed-2.0-pro and the lite Version

Capability	Doubao-Seed-2.0-pro	Doubao-Seed-2.0-lite
Model ID	doubao-seed-2-0-pro-260215	doubao-seed-2-0-lite-260215
Positioning	Flagship general-purpose	Balanced for high-frequency enterprise scenarios
Context window	1M tokens	1M tokens
Maximum output	65.5K tokens	65.5K tokens
Input modalities	Text, image	Text, image
Focus	Complex reasoning and long-chain execution	Balance of performance and cost
Best suited for	High-difficulty complex tasks	High-frequency production work

The Doubao series is billed in tiers by input length (32K / 128K / longer). Please refer to the real-time price card at the top of the page for details.

---

How to Use the Doubao-Seed-2.0-pro API

1. Create a SeaWhale AI API Key Generate a key in the console and top up your balance.

2. Note the Tiered Pricing The Doubao series is billed in three tiers by input token length. For the same task, keeping the context within 32K is far cheaper than exceeding 128K — it's worth optimizing your prompt design.

3. Call the API

curl -X POST https://api.seawhaleai.com/v1/chat/completions \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "doubao-seed-2-0-pro-260215",
    "messages": [
      {"role": "user", "content": "Based on this quarterly data, output a structured report containing three analysis dimensions, with each part no more than 300 words."}
    ],
    "stream": true
  }'

---

FAQ

How do I choose between Pro and lite? Choose Pro if you need complex reasoning, multi-step planning, or high-difficulty analysis; for high-frequency production work such as content creation, information processing, and data analysis, lite is sufficient and costs much less.

What are the context and output limits? 1M token context window, with a maximum output of 65,500 tokens.

Does it support video? Yes, it supports video content understanding. Please refer to the API documentation for specific input formats and limitations.

What exactly does "multi-constraint execution" mean? It means satisfying multiple mutually constraining requirements at the same time, such as 'use no more than 300 words, write in the third person, cite only the given materials, and output in JSON format' — this type of composite constraint is where the Pro version excels.

Why is the price divided into three tiers? The Doubao series is tiered by input token length (32K / 128K / longer), and the unit price for shorter inputs is significantly lower. Controlling context length is an effective way to reduce costs.

Is it suitable for enterprise-grade deployment? Yes. It is designed for complex business scenarios in the Agent era and performs stably in implementing complex rules and multi-constraint execution.

---

Why Choose SeaWhale AI for the Doubao-Seed-2.0-pro API

• No Volcano Engine Account Required — Call directly with a single key; no separate application needed
• OpenAI-Compatible Interface — Integrate by changing two lines in your existing code
• Flexible Switching Between Pro / lite — Route by task complexity for optimal cost
• RMB Settlement — Domestic models are priced in RMB for clear accounting

API

API integration

Model IDUse this value as the model in inference requests

doubao-seed-2-0-pro-260215

API KeyBearer token used to authenticate inference requests

Manage API keys

Base URLOpenAI compatible · /chat/completions

https://api.seawhaleai.com/v2/

provider OptionalSelects a service channel; omit it and the system picks the default

"provider": { "channel": "direct" }

doubao-seed-2-0-pro-260215 usage examples

SeaWhale AI is compatible with the OpenAI API protocol, so you can call it with the OpenAI SDK or plain HTTP requests. Streaming is enabled by default.

About the provider parameter (optional, a SeaWhale AI extension): most models are served over several channels that differ slightly in price and reliability. Add a provider field to the request body to pick one; omit it and the system selects the default channel — normal calls are unaffected.

provider is not part of the official OpenAI protocol — it is a SeaWhale AI extension that only takes effect on this platform. The OpenAI SDK allows custom fields like this to pass through; see the examples below.

Value	Channel	Best for
direct	Direct	The official upstream link, for native behavior and the full context window
stable	Preferred	Balanced availability and speed — a good default for production traffic
economical	Economy	Cost first, well suited to batch processing and price-sensitive workloads

Available channels and their prices are listed under "Pricing" above (channels vary by model). Additional notes:

• Syntax: "provider": { "channel": "direct" }.
• If the requested channel is not enabled for that model, the request automatically falls back to the default channel and returns normally — it does not error.
• With the official SDKs: in Python pass it via extra_body; in Node.js put it directly on the request object and it passes through. In TypeScript projects, add a // @ts-expect-error line to skip the type check.

cURL

curl https://api.seawhaleai.com/v2/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "doubao-seed-2-0-pro-260215",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "provider": { "channel": "direct" },
    "stream": true
  }'
# provider is optional — remove this line to use the default channel

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.seawhaleai.com/v2",
    api_key="<API_KEY>",
)

stream = client.chat.completions.create(
    model="doubao-seed-2-0-pro-260215",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
    stream=True,
    # Optional: pick a service channel; omit to use the default
    extra_body={"provider": {"channel": "direct"}},
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Node.js

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.seawhaleai.com/v2',
  apiKey: '<API_KEY>',
})

const stream = await client.chat.completions.create({
  model: 'doubao-seed-2-0-pro-260215',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' },
  ],
  stream: true,
  // Optional: pick a service channel; omit to use the default
  // @ts-expect-error provider is a SeaWhale AI extension, not in the OpenAI SDK types
  provider: { channel: 'direct' },
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
}