Seed 2.1 Turbo API

Seed 2.1 Turbo is a large language model by ByteDance Seed, available on the Venice API as seed-2-1-turbo. Requests are anonymized, so the provider never sees your identity.Seed 2.1 Turbo (Dola-Seed-2.1) is ByteDance’s next-generation multimodal model for the coding and agent era, with engineering-grade code delivery, long-horizon agent execution, and upgraded GUI and video understanding. Supports text, image, and video inputs with a 256K context window.

Seed 2.1 Turbo API pricing

Model ID	Variant	Privacy	Price
`seed-2-1-turbo`	Standard	Anonymized	$0.63 input /$ 3.13 output per 1M tokens

Seed 2.1 Turbo specifications

Spec	Value
Provider	ByteDance Seed
Released	Jun 28, 2026
Privacy	Anonymized
Context window	250K tokens
Max output	64K tokens
Reasoning effort	Not adjustable

How to use the Seed 2.1 Turbo API

Send requests to POST https://api.venice.ai/api/v1/chat/completions with "model": "seed-2-1-turbo" and your API key.

curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seed-2-1-turbo",
    "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
  }'

Seed 2.1 Turbo API FAQ

How much does the Seed 2.1 Turbo API cost?

0.63 per 1M input tokens and

3.13 per 1M output tokens, with cached input at $0.13 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the Seed 2.1 Turbo model ID?

Use seed-2-1-turbo as the model parameter.

Is the Seed 2.1 Turbo API private?

Seed 2.1 Turbo is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

What is the context window of Seed 2.1 Turbo?

250K tokens of context, with up to 64K output tokens per response.

What does Seed 2.1 Turbo support?

Seed 2.1 Turbo supports function calling, structured outputs, reasoning, image input, web search and prompt caching.

Which endpoint does the Seed 2.1 Turbo API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

NVIDIA Nemotron 3 Ultra API: $0.63 input /$ 3.13 output per 1M tokens
Grok Build 0.1 API: $1.00 input /$ 2.00 output per 1M tokens
Aion 3.0 Mini API: $0.88 input /$ 1.75 output per 1M tokens
Kimi K2.7 Code API: $0.75 input /$ 3.50 output per 1M tokens

Explore

By modality