Doubao Seed 2.0 Mini API
Doubao Seed 2.0 Mini is the cheap production default on NextModel at $0.03 input and $0.3 output per 1M tokens, for classification, short summaries, and other jobs where a long answer is a bug. The page lists the public id you send to the OpenAI-compatible endpoint, the listed input and output price, and the cases where you should escalate to a stronger model instead of squeezing this one.

| Input length | Input / 1M | Output / 1M | Cache hit / 1M |
|---|---|---|---|
| — - 32k | $0.03 | $0.3 | $0.01 |
| 32k - 128k | $0.06 | $0.59 | $0.02 |
| 128k - 256k | $0.12 | $1.18 | $0.03 |
What is Doubao Seed 2.0 Mini API in NextModel?
Doubao Seed 2.0 Mini is the cheap production default on NextModel at $0.03 input and $0.3 output per 1M tokens, for classification, short summaries, and other jobs where a long answer is a bug. The page lists the public id you send to the OpenAI-compatible endpoint, the listed input and output price, and the cases where you should escalate to a stronger model instead of squeezing this one.
Best use cases
- You already know the output shape: a label, a short rewrite, a routing decision.
- Volume is high enough that a premium model's output tokens would dominate the bill.
- You can keep a fallback model behind the same base URL when this one is wrong.
When not to use
- The user will read the answer as-is and you cannot stand a thin or sloppy paragraph.
- The prompt needs a large repo, a long PDF, or multi-step tool use.
- You have not tested it on your own Chinese or English samples yet.
OpenAI-compatible code example
Keep the OpenAI SDK style, set base_url to NextModel, and use the catalog model ID doubao-seed-2-0-mini.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.nextmodel.app/v1"
)
resp = client.chat.completions.create(
model="doubao-seed-2-0-mini",
messages=[{"role": "user", "content": "Hello from NextModel"}]
)
print(resp.choices[0].message.content)Similar alternatives
Available through the NextModel gateway via Volcengine.
Available through the NextModel gateway via Volcengine.
Available through the NextModel gateway via Volcengine.
Reading
Articles that explain Doubao Seed 2 0 Mini
Doubao Seed 2.0 Mini API guide: pricing, use cases, and OpenAI-compatible calls
First-party guide for this exact catalog entry.
Lin Qiming
Bad Hit Rate: the metric every LLM cache needs
Doubao Seed 2.0 Mini has a measured 50% Safe Hit Rate and 0% Bad Hit Rate.
Lin Qiming
How to estimate AI API cost before you ship
This is the cheap default. Price only helps if the output is short enough.
Lin Qiming
FAQ
Doubao Seed 2 0 Mini API questions
What model id do I send for Doubao Seed 2.0 Mini?
Send doubao-seed-2-0-mini to https://api.nextmodel.app/v1. Keep your OpenAI SDK. If that id is missing from /v1/models, the page is stale and you should not ship traffic.
When should I stop using Seed 2.0 Mini?
Move up when reviews, agents, or final customer answers start failing in ways a cheaper model cannot fix. Price is not a reason to stay.