How to Use Seed 2.0 Lite in Gemini
Seed 2.0 Lite suits document analysis, visual understanding, and multi-step tasks that need responsive answers. It balances quality and speed, while Seed 2.0 Pro focuses on long-chain reasoning and complex workflows.
Prompts to try with Seed 2.0 Lite in Gemini
Copy an example into Gemini, or ask in your own words.
Use Seed 2.0 Lite to compare the two reports supplied here. List changed claims and figures, with page references.
Use Seed 2.0 Lite to explain this chart in plain English. Preserve units and distinguish printed values from estimates.
Use Seed 2.0 Lite to summarize the visible actions in this video in chronological order. Include timestamps and mark uncertain observations.
Use Seed 2.0 Lite to extract dates, organizations, and measurements from this report into a table. Write unknown when evidence is missing.
Use Seed 2.0 Lite with deeper reasoning to identify contradictions in the supplied specification. Quote the conflicting passages and suggest clarification questions.
How to set up Seed 2.0 Lite in Gemini
Pick the way that suits you. Each takes about two minutes.
Use the Gemini connector
- Open Connected Apps
On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.
- Add Spiral as a custom app
Under Custom apps, click Add a custom app and paste this MCP server URL:
https://api.spiral.ai/mcp
- Sign in to Spiral and approve
Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.
Use the Spiral skill
- Send Gemini this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Seed 2.0 Lite
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "bytedance-seed/seed-2.0-lite", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Gemini finds Seed 2.0 Lite on Spiral, shows the price and runs it.
Seed 2.0 Lite providers and prices
Spiral runs Seed 2.0 Lite through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.010662 per run at the default inputs. $0.325 per 1M input tokens, $2.60 per 1M output tokens.
Settings you can ask for
Ask Gemini for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Top p | 0 to 1 | ||
| Max tokens | 1 to 131072 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Reasoning effort | none, minimal, low, medium, or high | medium | How much the model reasons. |
| Frequency penalty | -2 to 2 |
Every API field of ByteDance Seed: Seed-2.0-Lite is on its tool page: open its card above.
What can you do with Seed 2.0 Lite in Gemini?
Turn dense reports, charts, and video into answers you can inspect with Seed 2.0 Lite. Ask for source references and a clear separation between observations and conclusions.
Extract report data
Turn report pages into records with dates, measurements, units, and supporting page references. Mark missing values explicitly.
Explain charts
Read chart labels and trends, then explain what the plotted evidence supports. Separate visible values from estimates.
Build from a visual reference
Translate a screenshot into an interface implementation, then refine the layout through inspection and testing.
Work through a software issue
Use requirements, relevant code, and test results to propose a focused patch and revise it after validation.
Recap visible video events
Summarize actions and their sequence in a video. Ask for timestamps and flag uncertain observations.
Compare long documents
Compare specifications or reports for changed requirements, conflicting statements, and unanswered questions, with references to the source passages.
More on Seed 2.0 Lite and Gemini
Overview
Seed 2.0 Lite in other agents
Questions about Seed 2.0 Lite in Gemini
Can Gemini use Seed 2.0 Lite?
Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Seed 2.0 Lite like any built-in tool.
How much does Seed 2.0 Lite cost in Gemini?
Up to $0.010662 per run at the default inputs. $0.325 per 1M input tokens, $2.60 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.
Do I need an OpenRouter account to use Seed 2.0 Lite in Gemini?
No. Spiral runs Seed 2.0 Lite on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Seed 2.0 Lite in Gemini?
About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.
Does Gemini wait while Seed 2.0 Lite runs?
Seed 2.0 Lite runs in the background. Gemini starts the run, checks on it and gives you the text, json when it's ready.
What is Seed 2.0 Lite good at?
Seed 2.0 Lite suits reading dense documents, interpreting charts, and turning source material into structured answers. ByteDance positions it as a balance between answer quality and response speed.
How does Seed 2.0 Lite compare with Seed 2.0 Pro?
Seed 2.0 Lite balances quality and speed for general-purpose work. Seed 2.0 Pro emphasizes long-chain reasoning and robustness in complex workflows.
How much context and output can Seed 2.0 Lite handle?
The listed endpoint supports a 262,144-token context window and up to 131,072 completion tokens. Treat those as ceilings when planning a task, and request only the answer length you need.
Can Seed 2.0 Lite generate images or videos?
Seed 2.0 Lite produces text. Use it to explain a chart, describe a scene, or summarize a video.
Which setting matters most for complex tasks?
Reasoning effort is a useful starting point: BytePlus recommends high effort for agent work. Lower reasoning depth can improve speed, so reserve deeper analysis for tasks that need it.
Start using Seed 2.0 Lite in Gemini
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini:
set up https://spiral.ai/SKILL.md


