Latency-focused multimodal model with 256K context, four reasoning effort modes, and image/video understanding for high-concurrency use.
ByteDanceText Generation256K contextMalaysiaProprietary EndpointLatency-focused multimodal model with 256K context, four reasoning effort modes, and image/video understanding for high-concurrency use.
Also known as Seed Mini, Seed-2.0-Mini
seed-2-0-miniPOST /v1/chat/completionsPOST /v1/responsesPOST /v1/messagesLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Seed 2.0 Mini serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id seed-2-0-mini. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seed-2-0-mini",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="seed-2-0-mini",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Seed 2.0 Mini API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| temperature | number | 0.7 | 0 to 2 | Sampling temperature |
| top_p | number | 1 | 0 to 1 | Nucleus sampling |
| max_tokens | number | 4096 | 1 to 65536 | Max output tokens |
| frequency_penalty | number | 0 | -2 to 2 | Penalty for repeated tokens. >0 reduces repetition, <0 encourages it. |
| presence_penalty | number | 0 | -2 to 2 | Penalty for new vs. seen tokens. >0 encourages new topics, <0 encourages staying on topic. |
| stop | string | - | - | Comma-separated stop sequences |
| enable_thinking | boolean | true | - | Enable deep thinking / reasoning mode. |
| reasoning_effort | enum | medium | low, medium, high | Reasoning effort tier. Use enable_thinking=false to disable reasoning entirely. |
| enable_web_search | boolean | false | - | Enable BytePlus Ark MCP web search. |
| enable_caching | boolean | false | - | Cache the prompt prefix for ~10 min so follow-up requests reuse it and pay fewer input tokens for the cached portion. |
| image_detail | enum | high | low, high, xhigh | Image visual quality tier for vision input. |
| video_fps | number | - | 0.2 to 5 | Frames per second extracted from video input. |
Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.
On EmpirioLabs, Seed 2.0 Mini is billed pay as you go: Input <=128K $0.12; 128K-256K $0.24 per 1M prompt tokens; Output <=128K $0.50; 128K-256K $1.00 per 1M generated tokens. The live rate card on this page always matches what the API charges.
Seed 2.0 Mini supports a 256K-token context window with up to 128,000 output tokens per response.
Yes. Seed 2.0 Mini serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to seed-2-0-mini.
Yes. The EmpirioLabs playground runs Seed 2.0 Mini in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
