Seed 2.1 Turbo API

ByteDance Seed's Seed 2.1 Turbo, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send seed-2.1-turbo as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: seed-2.1-turbo
Maker: ByteDance Seed
Context window: 229.1K tokens
Input price: $0.630 per million tokens
Output price: $3.130 per million tokens
Providers: 1 independent provider
Regions: global

Providers

EmpirioLabs AI: global, $0.630 input and $3.130 output per million tokens, $0.630 cache read per million tokens, 229.1K tokens of context

Scores

HLE: 4.1, #226 of 273
GPQA: 41.0, #228 of 250
LiveCodeBench: 16.3, #112 of 130
MMLU-Pro: 63.3, #109 of 133
SimpleQA Verified: 29.7, #80 of 126

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seed-2.1-turbo",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Seed 2.1 Turbo?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Seed 2.1 Turbo cost?: Offers now ask $0.630 per million input tokens and $3.130 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Seed 2.1 Turbo?: The largest offer takes 229,093 input tokens. One job can generate up to 65,536 tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Seed 2.1 Turbo do?: Its providers list Vision, Video input, Reasoning effort, JSON object, JSON schema, Frequency penalty, Presence penalty, Stop sequences, Text, Tools.
What inputs and outputs does Seed 2.1 Turbo support?: Text · Images · Video → Text.
Which providers serve Seed 2.1 Turbo?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Seed 2.1 Turbo?: Send "seed-2.1-turbo" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Seed 2.1 Turbo listed?: The exchange first listed it on 10/8/2026. This is not its release date.