Type
Spec
Rate
Input
per 1M prompt tokens
<=128K $0.40 128K-256K $0.80
Output
per 1M generated tokens
<=128K $2.40 128K-256K $4.80
Seed 2.0 Code and Seed 2.0 Lite side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
ByteDance Text GenerationSeed 2.0 Code and Seed 2.0 Lite are both ByteDance models in the Text Generation category, available through the EmpirioLabs API.
| Spec | Seed 2.0 Code | Seed 2.0 Lite |
|---|---|---|
| Model ID | seed-2-0-code | seed-2-0-lite |
| Author | ByteDance | ByteDance |
| Released | Feb 14, 2026 | Feb 14, 2026 |
| Context window | 229.1K tokens | 229.1K tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Input | Text Image Video Document | Text Image Video Document |
| Output | Text | Text |
| Structured output | Not supported | JSON Schema |
| Batch API | - | Available |
| Region | Malaysia | Malaysia |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/seed-2-0-code:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/seed-2-0-lite:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Seed 2.0 Code | Seed 2.0 Lite |
|---|---|---|
| max_tokens | 1 to 128000 | 1 to 128000 |
| frequency_penalty | -2 to 2 Default: 0 | -2 to 2 Default: 0 |
| presence_penalty | -2 to 2 Default: 0 | -2 to 2 Default: 0 |
| stop | string | string |
| enable_thinking | boolean Default: true | boolean Default: true |
| reasoning_effort | low, medium, high Default: medium | low, medium, high Default: medium |
| enable_web_search | boolean Default: false | boolean Default: false |
| max_tool_calls | 1 to 10 Default: 3 | 1 to 10 Default: 3 |
| image_detail | low, high, xhigh Default: high | low, high, xhigh Default: high |
| video_fps | 0.2 to 5 | 0.2 to 5 |
| response_format | - | enum |
Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.
Pricing is 2x when input tokens >=128K. Temperature and top_p are server-fixed (temp=1, top_p=0.95) regardless of client value.
Seed 2.0 Code 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-code. Both models are called through the same endpoint. Set model to seed-2-0-code or seed-2-0-lite. 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-code",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Both models were released on Feb 14, 2026. Both models have a context window of 229.1K tokens. Capabilities listed only for Seed 2.0 Code: code interpreter, agentic coding. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.