DeepSeek-V3.2 is a general-purpose Mixture-of-Experts (MoE) large language model from DeepSeek AI that harmonizes high computational efficiency with superior reasoning and agent performance. It features 685 billion total parameters, supports a 164Ktoken context window, and is natively calibrated for tool use and function calling in complex agentic workflows.

DeepSeek-V4-Flash is a highly efficient Mixture-of-Experts (MoE) language model featuring 158B total parameters with only 13B activated during inference. It utilizes a Hybrid Attention Architecture (combining Compressed Sparse Attention and Heavily Compressed Attention) to natively and efficiently support a 1-million-token context window. The model offers switchable reasoning modes (Non-think, Think High, and Think Max) and excels at high-speed generation for reasoning, coding, tool-calling, and agentic tasks.

DeepSeek-V4-Pro is a flagship Mixture-of-Experts (MoE) language model with 862B total parameters (49B activated) and a 1-million-token context window. It features a Hybrid Attention Architecture combining Compressed Sparse Attention and Heavily Compressed Attention for efficient long-context processing. With multiple distinct reasoning modes (such as Think Max for maximum reasoning effort), it is built for advanced mathematical reasoning, software engineering, tool use scenarios, and complex long-horizon agentic workflows.

Dola-Seed 2.1 Turbo is a next-generation multimodal large model by ByteDance designed for real-world productivity, high-value production tasks in enterprise R&D, and large-scale agentic scenarios. It features comprehensive upgrades in coding engineering delivery, long-horizon agent task execution, and multimodal understanding, along with stronger autonomous planning and dynamic self-repair capabilities.

GLM-5.2 is Z.ai's latest flagship open-weights MoE model engineered specifically to dominate long-horizon autonomous coding and engineering tasks. It features a solid 1-million-token context window, multiple thinking effort levels, and an improved IndexShare architecture that significantly boosts reasoning and agentic performance.

A model from ByteDance featuring adaptive thinking (AdaCoT) to control reasoning length. It was developed from Seed1.5-Thinking with greater training compute and integrated VLM capabilities. Supports text and image inputs with a 256K context window

ByteDance Seed 1.6 Flash is an ultra-fast multimodal deep-thinking model optimized for speed and cost-efficiency without compromising capability. It supports text, image, and video inputs along with tool use and function calling across an expansive 256K token context window, making it ideal for high-speed automated workflows and media-heavy processing.

ByteDance Seed 1.8 is a large language model optimized for long-context reasoning and generation with a 256K context window. It excels in complex coding, multi-turn dialogue, and multi-step agentic tasks while robustly supporting vision inputs and parallel tool calling.

Dola-Seed 2.0 Code is ByteDance's dedicated coding model optimized for enterprise-level programming needs. It excels in agentic task planning with rational decomposition and dynamic self-repair, while inheriting the Seed 2.0 family's robust multimodal perception to read charts, screenshots, and diagrams for contextually accurate code generation.

Model	Category	Input	Output	Context	Pricing
deepseek-v3-2-251201 2c7c25b34d1947ed99ce971e176be983	text	text	text	164K	$0.280 in / $0.420 out
deepseek-v4-flash-260425 0fa38dcc8d014138b2f7049951532a9e	text	text	text	1M	$0.140 in / $0.280 out
deepseek-v4-pro-260425 b348948916bf49c58cb451cec8f119f4	text	text	text	1M	$1.740 in / $3.480 out
dola-seed-2-1-turbo-260628 7407962990374715951c4dd6bce557a5	text	text, image, video	text	256K	$0.500 in / $2.500 out
glm-5-2-260617 d7b7ad781cc64967a06e1047e65414b0	text	text	text	1M	$1.400 in / $4.400 out
seed-1-6-250915 6d5b880a25d941ee963e678f270b5549	text	text, image, video	text	256K	$0.250 in / $2.000 out
seed-1-6-flash-250715 6aa7218e46834124af83c49f34d764c7	text	text, image, video	text	256K	$0.075 in / $0.300 out
seed-1-8-251228 7174e0cf80c04dae8560b21102afee79	text	text, image, video	text	256K	$0.250 in / $2.000 out
seed-2-0-code-preview-260328 834e132654da45c385e65e4b51edf50a	text	text, image, video	text	256K	$0.500 in / $3.000 out

bytedance models on OneInfer

Categories

Modalities

API access

bytedance model catalog