YepAPI
AI Models

Seed 2.1 Turbo

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows, suited for end-to-end software delivery, multi-step task execution and understanding visual and video input. ByteDance Multimodal Coding Agent, with a 256K token context window.

POST/v1/ai/chat
$0.01/call

Overview

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows, suited for end-to-end software delivery, multi-step task execution and understanding visual and video input. ByteDance Multimodal Coding Agent, with a 256K token context window.

PropertyValue
Model IDbytedance-seed/seed-2-1-turbo
Context Window262,144 tokens
Max Output235,929 tokens
Input Price$0.74 / 1M tokens
Output Price$3.69 / 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-2-1-turbo',
    messages: [{ role: 'user', content: 'Turn this screenshot of a Figma mockup into a Tailwind component.' }],
  }),
});
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-2-1-turbo", "messages": [{"role": "user", "content": "Turn this screenshot of a Figma mockup into a Tailwind component."}]}'

Request Body

ParameterTypeRequiredDescriptionDefault
modelstringYesModel ID (e.g. bytedance-seed/seed-2-1-turbo)—
messagesMessage[]YesArray of { role, content } objects—
maxTokensnumberNoMaximum tokens in the responseModel default
temperaturenumberNoSampling temperature (0.0–2.0)1.0
topPnumberNoNucleus sampling threshold1.0
frequencyPenaltynumberNoPenalize repeated tokens0
presencePenaltynumberNoPenalize tokens already present0
streambooleanNoEnable SSE streamingfalse
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-2-1-turbo",
    "message": {
      "role": "assistant",
      "content": "A card with a rounded border, a 48px avatar on the left, a two-line title and subtitle, and a ghost button aligned right; implemented as a flex row with gap-4, p-4 and rounded-xl border classes."
    },
    "usage": {
      "promptTokens": 16,
      "completionTokens": 245,
      "totalTokens": 261
    }
  }
}

Streaming

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

data: {"delta":{"content":"Use"},"model":"bytedance-seed/seed-2-1-turbo","index":0}
data: [DONE]
Under the Hood

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

On this page