Seed2.1 Turbo
Seed2.1 Turbo is the efficient, high-throughput model of ByteDance Seed's Seed2.1 family, with deep reasoning, multimodal understanding and tool use and a 256K context, offered on BytePlus ModelArk as Dola-Seed-2.1-Turbo.
Released
June 23, 2026
Type
multimodal
License
proprietary
Context
—
The developer states a context window of “256K” tokens.
Pricing
Input
$0.50 / 1M tokens
Output
$2.50 / 1M tokens
List price on the developer's own pages, checked . BytePlus ModelArk (international), standard online inference with prompts up to 256K tokens. Cache-hit input $0.10; cache storage $0.0083 per 1M tokens per hour. Flex and batch $0.25 input / $1.25 output. On Volcano Engine in China it is ¥3 / ¥15.
Capabilities
Sources
Every figure on this page was checked against these pages on . A figure we could not source is left out.
- ByteDance Seed blog: Seed2.1 Officially Released (2026-06-23) (opens in a new tab)
- ByteDance Seed: Seed2.1 page (opens in a new tab)
- BytePlus ModelArk: Model list (opens in a new tab)
- BytePlus ModelArk: Pricing (opens in a new tab)
- Seed2.1 Model Card (PDF) (opens in a new tab)
Spotted something out of date? Tell us.
Links
In the news: Seed2.1 Turbo and ByteDance Seed
MarkTechPost
Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
HarnessDev, a novel framework developed by researchers from ByteDance Seed, Singapore University of Technology and Design, Georgia Institute of Technology, M-A-P, and TokenWave.AI, shifts the focus of large language model (LLM) evaluation from task completion to the LLM's capacity to engineer its own agent harness. An agent harness is defined as the surrounding code that enables an LLM to execute tasks, encompassing its execution loop, tool integration, context management, state tracking, error recovery, and verification mechanisms. This contrasts with traditional benchmarks, such as the Terminal-Bench 2.1 leaderboard, where the harness is typically fixed, and LLMs like GPT-5 exhibit varying performance (35.2% on Terminus 2 versus 49.6% on Codex CLI with identical weights). HarnessDev proposes a two-stage process: Creation and Evolution. In the Creation stage, each LLM begins with a rudimentary set of passive primitives—file access, search, and process execution—along with result and trajectory writers, but lacks essential components like a loop, planner, verifier, retry logic, or stopping rule. Unmodified, these initial harnesses score zero on all tasks. The LLM is then provided with a task-family specification, a design tutorial, and a few development cases to construct a functional harness, which is subsequently frozen before being tested on hidden tasks. The Evolution stage allows the LLM to refine its frozen Creation harness by incorporating feedback from execution on a fixed set of 100 SWE-bench Pro tasks and all 89 Terminal-Bench 2.1 tasks. Official candidate harnesses must successfully navigate both evaluation phases, with a budget of 10 harness pairs and a maximum of two five-task probes between pairs. Ultimately, each official harness version is assessed on 630 held-out SWE-Pro instances that the creator LLM never encountered during development. Harnesses are graded on two primary metrics: capability, measured by task success rate, and efficiency, quantified by the number of executor tokens consumed, excluding the creator LLM's own tokens. The evaluation involved six creator LLMs: Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek V4 Pro, Qwen 3.7 Max, and Seed 2.0 Pro. These models operated within the Claude Code 2.1.177 environment, with GPT-5.5 utilizing Codex 0.144.3. The Creation phase spanned four domains and five benchmarks, comprising a total of 2,207 instances: the public split of SWE-bench Pro (731 instances), Terminal-Bench 2.1 (89 instances), MLE-bench (75 instances), EQ-Bench3 (46 instances), and BrowseComp (1,266 instances). Each creator LLM was tasked with building three harnesses per benchmark, with results reported as an average at the 3-task success rate (avg@3). The framework's design aims to assess the LLM's meta-cognitive abilities in self-improvement and system design, moving beyond simple problem-solving to the construction of the problem-solving infrastructure itself. This approach is crucial for developing more autonomous and adaptable AI agents capable of self-modification and optimization in complex environments.
MarkTechPost
ByteDance Seed and Tsinghua AIR Introduces CUDA Agent: A Large-Scale Agentic RL System for CUDA Kernel Generation
ByteDance Seed and Tsinghua AIR have introduced CUDA Agent, a large-scale agentic reinforcement learning system designed to generate optimized GPU kernels for CUDA. This system trains a large language model to produce CUDA code that significantly outperforms standard compiler optimizations. The primary challenge CUDA Agent addresses is the generation of efficient, rather than merely correct, CUDA code. Prior to this development, frontier AI models could generate functional CUDA kernels, but these often lagged behind the performance achieved by compiler optimizations. On the KernelBench benchmark, the base model, Seed1.6, demonstrated a 74.0% task completion rate but only surpassed torch.compile in performance for 27.2% of tasks, exhibiting a geometric-mean speedup of 0.69×, indicating its kernels were generally slower than compiler-generated ones. CUDA Agent was trained within a comprehensive CUDA development environment that included profiling tools, correctness verification, and a permission-locked sandbox. This training utilized Proximal Policy Optimization (PPO) over 150 steps with a substantial 131,072-token context window. The result of this intensive training is a remarkable 98.8% task pass rate and a 96.8% rate of outperforming torch.compile across a 250-task benchmark. The system achieved a geometric-mean speedup of 2.11× over standard compilation, positioning it approximately 40 points ahead of advanced models like Claude Opus 4.5 and Gemini 3 Pro on the most challenging Level-3 tasks. While the full trained agent has not been released, the research team has made public several components: the CUDA-Agent-Ops-6K dataset, the SKILL.md specification, and the reward and anti-reward-hacking recipes. The underlying model, Seed1.6, is a proprietary Mixture-of-Experts (MoE) model featuring 23 billion active parameters and a total of 230 billion parameters. The development and training process required significant computational resources, with the profiling sandbox alone utilizing 128 NVIDIA H20 GPUs. This level of resource intensity suggests that full replication is feasible primarily within frontier research labs, large GPU cloud providers, and major infrastructure teams. However, mid-sized teams can still leverage key components such as the dataset, milestone reward system, and skill specification, integrating them with open-source base models. The applications for CUDA Agent span various industries and critical computational domains. These include AI infrastructure and inference serving, GPU cloud computing, autonomous driving systems, quantitative trading platforms, medical imaging analysis, and recommendation systems. Essentially, any area where fused kernels are on a latency-critical path can benefit. Specific use cases involve optimizing operator sequences that torch.compile handles poorly, reducing the cost per token in AI model inference, and re-tuning kernels to adapt to new generations of GPUs. The research also touches upon data synthesis techniques, with the team crawling reference operations to enhance the training data.