Dola-Seed 2.0 Code is ByteDance's dedicated coding model.
ByteDance's Seed 2.0 launch post says the Seed2.0 Pro and Code models were launched on the Doubao App and TRAE, with the full Seed2.0 model API available on Volcano Engine.
| Developer | ByteDance |
|---|---|
| Model ID | bytedance/seed-2-0-code-preview |
| Release Date | April 23, 2026 |
| Context Window | 256,000 tokens (~256K) |
| Max Output Tokens | 128,000 tokens |
| Modalities | Image, Text, Video → Text |
| Capabilities | parallel tool calls, reasoning, streaming, tool/function calling, vision |
Dedicated coding model
Described as ByteDance's dedicated coding model and part of the Seed 2.0 family.
Launch association
ByteDance states that the Seed2.0 Pro and Code models were launched together in the Seed 2.0 release.
Platform availability
ByteDance says the model API for the full Seed2.0 series is available on Volcano Engine.
Model identity
The exact model id shown in search results is tied to the Seed 2.0 Code preview listing for ByteDance.
Software engineering tasks
Positioned for coding-focused work in the Seed 2.0 lineup.
Agent workflows
Presented as a code model intended for use alongside ByteDance's app and API ecosystem.
Sources: https://gate.ai/blog/seed2-0-code-preview-bytedance-specs-pricing-api-access-use-cases · https://seed.bytedance.com/en/blog/seed-2-0-official-launch · https://developer.puter.com/ai/byteplus/seed-2-0-code-preview-260328/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Repository-aware bug investigation and multi-file changes are documented as a fit for this model.
Refactoring and framework or dependency migrations are documented as suitable use cases.
Test generation tied to existing implementations is documented as a use case.
Long technical prompts containing code, logs, and specifications are also documented as suitable.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "bytedance/seed-2-0-code-preview", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "bytedance/seed-2-0-code-preview", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"bytedance/seed-2-0-code-preview","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
Preview status means the API interface, benchmark performance, and pricing are subject to change or discontinuation without the same stability guarantees as a generally available release.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Dola-Seed 2.0 Code This page | Multimodal reasoning | |||
| Reasoning + agents | ||||
| Reasoning + agents | ||||
| Reasoning + agents |
Dola-Seed 2.0 Code has a 256,000 tokens context window and can return up to 128,000 tokens.
Dola-Seed 2.0 Code takes image, text, video as input and returns text.
Use bytedance/seed-2-0-code-preview as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Dola-Seed 2.0 Code became available on April 24, 2026.
Dola-Seed 2.0 Code is priced at input $0.65 / 1M tokens, output $3.9 / 1M tokens, cached input $0.13 / 1M tokens.
Yes, Dola-Seed 2.0 Code can stream responses as they are generated.
Yes, Dola-Seed 2.0 Code accepts image input alongside text.
Dola-Seed 2.0 Code was built by ByteDance.
Yes, it supports tool calling, including parallel tool calls.
