Seed 2.1 Turbo

Seed 2.1 Turbo is a faster variant of ByteDance's Seed 2.1 model, designed for multimodal reasoning and latency-sensitive agent workflows. It is part of the seed line and was released on 2026-06-23, the same day as Seed 2.1 Pro. It has a context window of 256,000 tokens and a maximum output of 256,000 tokens. It accepts image, text, and video input and returns text. It supports reasoning mode and tool calling. The weights are not open. Pricing starts at $0.4453 per million input tokens and $2.23 per million output tokens, with cached input at $0.0891 per million tokens.

Against Seed 2.0 Pro: input $0.475 to $0.4453, output $2.37 to $2.23, cached input $0.095 to $0.0891.

• ·256k token context and output window
• ·Accepts image, text, and video input
• ·Supports reasoning mode and tool calling
• ·Designed for latency-sensitive agent workflows

• Reach for it for multimodal reasoning on image, text, and video
• Reach for it for latency-sensitive agent workflows
• Reach for it for tool-calling agents with long context

1 host serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and output limit?

Context window is 256,000 tokens, and max output is also 256,000 tokens.

What input modalities does it support?

It accepts image, text, and video input, and returns text output.

What is the pricing?

Input from $0.4453 per million tokens, output from $2.23 per million tokens, cached input from $0.0891 per million tokens.