Seed 2.0 Pro

Seed 2.0 Pro is ByteDance's flagship Seed 2.0 reasoning model for complex reasoning, coding and agents, with a 262K context window.

POST/v1/ai/chat

$0.01/call

Overview

Seed 2.0 Pro is ByteDance's flagship Seed 2.0 model, a reasoning model for complex problem solving, coding and agent workflows. It returns its reasoning alongside the answer, accepts text and image input, and has a 262K context window.

Property	Value
Model ID	`bytedance-seed/seed-2.0-pro`
Context Window	262,144 tokens
Max Output	131,072 tokens
Input Price	$0.74 / 1M tokens
Output Price	$4.43 / 1M tokens

Usage

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'bytedance-seed/seed-2.0-pro',
    messages: [{ role: 'user', content: 'Find the bug in this function and explain the fix step by step.' }],
  }),
});
const { data } = await res.json();
console.log(data.message.content);

curl -X POST https://api.yepapi.com/v1/ai/chat \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bytedance-seed/seed-2.0-pro", "messages": [{"role": "user", "content": "Find the bug in this function and explain the fix step by step."}]}'

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `bytedance-seed/seed-2.0-pro`)	—
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`maxTokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`topP`	`number`	No	Nucleus sampling threshold	`1.0`
`frequencyPenalty`	`number`	No	Penalize repeated tokens	`0`
`presencePenalty`	`number`	No	Penalize tokens already present	`0`
`stream`	`boolean`	No	Enable SSE streaming	`false`

Info

All AI models use the /v1/ai/chat endpoint. Specify the model with the model field.

Response

{
  "ok": true,
  "data": {
    "model": "bytedance-seed/seed-2.0-pro",
    "message": {
      "role": "assistant",
      "content": "The loop runs one index past the end of the array because the condition uses <= instead of <. Changing it to i < items.length stops the out-of-bounds read on the last iteration."
    },
    "usage": {
      "promptTokens": 16,
      "completionTokens": 245,
      "totalTokens": 261
    }
  }
}

Pricing

Prompt size	Input $/M	Output $/M
Up to 128K tokens	$0.74	$4.43
Over 128K tokens (long-prompt tier)	$1.48	$8.86

Reasoning tokens bill as output. Aliases: seed-2.0-pro, seed-pro.

Info

Seed 2.0 Pro is a reasoning model. Its thinking is returned in the reasoning field of the message (and of each streamed delta).

Streaming

Set "stream": true to receive Server-Sent Events. Each chunk contains a delta object:

data: {"delta":{"content":"Use"},"model":"bytedance-seed/seed-2.0-pro","index":0}
data: [DONE]

Under the Hood

We handle auth, billing, and response normalization — you just send messages.