by Doubao
Seed-OSS is a series of open-source large language models developed by ByteDance's Seed team, designed specifically for powerful long-context processing, reasoning, agents, and general capabilities. Among this series, Seed-OSS-36B-Instruct is an instruction-tuned model with 36 billion parameters that natively supports ultra-long context lengths, enabling it to process massive documents or complex codebases in a single pass. This model is specially optimized for reasoning, code generation, and agent tasks (such as tool usage), while maintaining balanced and excellent general capabilities. A notable feature of this model is the "Thinking Budget" functionality, which allows users to flexibly adjust the inference length as needed, thereby effectively improving inference efficiency in practical applications.
Seed-OSS is a series of open-source large language models developed by ByteDance's Seed team, designed specifically for powerful long-context processing, reasoning, agents, and general capabilities. Among this series, Seed-OSS-36B-Instruct is an instruction-tuned model with 36 billion parameters that natively supports ultra-long context lengths, enabling it to process massive documents or complex codebases in a single pass. This model is specially optimized for reasoning, code generation, and agent tasks (such as tool usage), while maintaining balanced and excellent general capabilities. A notable feature of this model is the "Thinking Budget" functionality, which allows users to flexibly adjust the inference length as needed, thereby effectively improving inference efficiency in practical applications.
ByteDance-Seed/Seed-OSS-36B-Instruct has a 256,000 token context window.
On AIHubMix, ByteDance-Seed/Seed-OSS-36B-Instruct costs $0.2 per million input tokens and $0.53 per million output tokens.
ByteDance-Seed/Seed-OSS-36B-Instruct accepts text and image input.
ByteDance-Seed/Seed-OSS-36B-Instruct supports thinking，tools, function calling and structured outputs. Per-protocol parameter support is listed in the capability table on this page.
ByteDance-Seed/Seed-OSS-36B-Instruct is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to ByteDance-Seed/Seed-OSS-36B-Instruct — no other code changes needed.
ByteDance-Seed/Seed-OSS-36B-Instruct is developed by Doubao. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
The Doubao large-model team has launched a new-generation professional-grade multimodal…
Seedance 2.0 fast is a next-generation multimodal video-creation model launched by the…
Doubao Coding model optimized for real-world programming environments that can reliably…
Doubao Coding model optimized for real-world programming environments that can reliably…
Doubao flagship all-purpose general model, targeting complex reasoning and long-chain…
The Doubao 2.0 series is a coding model optimized for real programming environments…
Use ByteDance-Seed/Seed-OSS-36B-Instruct via the AIHubMix unified API — one interface for every major LLM.