LLM & ChatActive
Seed V2 Lite LLM
A lightweight ByteDance language model for chat and tool calling, with image understanding and a 256K-token context window.
Overview
Seed V2 Lite is the lightweight member of ByteDance's Seed 2.0 family. It answers in text, reads images supplied alongside the prompt, and can call tools you define, which suits high-volume work where a larger model would be more than the task needs.
What you can build
- Chat assistants and support flows that stay responsive under load
- Tool-using agents that route requests into your own functions
- Summarisation, classification, and extraction over long documents
- Visual Q&A on screenshots, charts, and photos
Inputs
- A written prompt describing the task.
- Optional images in JPG/JPEG or PNG for visual understanding.
- Optional system instructions that set role, tone, and boundaries.
- Optional user and session identifiers, which keep one conversation's history together.
- Optional sampling controls: temperature, top P, and presence and frequency penalties.
- Optional reasoning effort, controlling how much the model works through before it answers.
Outputs
A text answer, plus any tool calls the model chooses to make for your client to execute.
Recommended settings
- Keep temperature near its default for factual work; raise it for drafting and ideation.
- Raise reasoning effort for multi-step problems, lower it for short and direct answers.
- Fit the prompt, attached images, and expected answer inside the 256K-token context window.
Limitations
- This is the lightweight model in the family; hard multi-step reasoning is better served by a larger Seed V2 model.
- Image understanding depends on input quality. Blurry captures, very small text, and heavy compression hide detail.
- It returns text only and does not generate images.
Safety & compliance
Follow ByteDance's usage policies for the prompts, images, and generated output you handle, and comply with the laws that apply to your use.
API quick start
Run seed-v2-lite with a single API call.
{
"prompt": "Tell me about Türkiye",
"inputImage": "https://your-cdn.com/input.png",
"user_id": "...",
"session_id": "..."
}curl -X POST "https://api.wiro.ai/v1/Run/bytedance/seed-v2-lite" \
-H "Content-Type: application/json" \
-H "x-api-key: YOUR_WIRO_API_KEY" \
--data-binary @- <<'JSON'
{
"prompt": "Tell me about Türkiye",
"inputImage": "https://your-cdn.com/input.png",
"user_id": "...",
"session_id": "..."
}
JSONOther models you might like
Explore similar llm & chat models.
