---
id: "bytedance-seed/seed-2-1-turbo"
also: ["bytedance-seed/seed-2-1-turbo-20260810", "vercel/bytedance/seed-2.1-turbo"]
cheapest_list_usd_per_m: "0.5 in, 2.5 out, at seed/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.4327 in, 2.5 out, at bytedance on vercel"
context: 262144
max_output: 235929
input: ["text", "image", "video"]
output: ["text"]
released: "2026-08-12"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 1
---
# ByteDance Seed: Seed 2.1 Turbo

Seed 2.1 Turbo is ByteDance’s multimodal language model supporting text, image, and video inputs with text output. It offers a 262,144-token context window, reasoning, function calling, and structured JSON output.