Seed 2.0 Code

ByteDance SeedMCP Tool CallReasoning
bytedance-seed/seed-2.0-codeClosed API

ByteDance Seed coding model for multimodal software engineering and long-running agents

Benchmark Pricing$0.50 / 1M in$3.00 / 1M out$0.25 cache read
Context: 262,144 tokens•Max Output: 131,072 tokens•Released: 2026-02-14

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens
Max Output131,072131.1K tokens
LicenseProprietaryCloud API only
Input Modalities
TextVisionVideo
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Seed 2.0 Code natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Seed 2.0 Code via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.BYTEDANCE-SEED_API_KEY,
});

const response = await client.chat.completions.create({
  model: "bytedance-seed/seed-2.0-code",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);

PRICING BY PROVIDER

12 providers
NanoGPTbytedance-seed/seed-2.0-code
$0.50 / $3.00$0.25 cache
AI/ML APIbytedance-seed/seed-2.0-code
$0.69 / $4.13
Volcengine Arkdoubao-seed-2-0-code-preview-260215
$0.47 / $2.37$0.10 cache
Ofoxvolcengine/doubao-seed-2.0-code
$0.67 / $3.36$0.14 cache
Merge Gatewaybytedance/dola-seed-2.0-code-preview
$0.50 / $3.00
Kilo Gatewaybytedance-seed/seed-2.0-code
$0.50 / $3.00
ZenMuxvolcengine/doubao-seed-2.0-code
$0.90 / $4.48
Deep InfraByteDance/Seed-2.0-code
$0.50 / $3.00$0.10 cache
Requestyseed-2.0-code
$0.50 / $3.00$0.10 cache
Qiniudoubao-seed-2.0-code
$0.46 / $2.32$0.09 cache
EmpirioLabs AIseed-2-0-code
$0.40 / $2.40$0.40 cache
OpenRouterbytedance-seed/seed-2.0-code
$0.50 / $3.00

Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.

Prompt Caching Active

This model supports prompt caching at $0.25 / 1M tokens, saving up to 50% on repetitive MCP tool definitions and system instructions.