Skip to main content
Source: BytePlus ModelArk docs. All models support tool/function calling. Models with an activation warning must be enabled in the Ark Console before use.

​
Seed 2.0

seed-2-0-pro-260328

Reasoning · Speedbyteplus/seed-2-0-pro-260328BytePlus’s flagship Seed 2.0 model. Excels at complex reasoning, coding, and agentic tasks with deep thinking capability and multimodal understanding across text, images, and video.
Activation required — enable in the Ark Console before first use.
  • ~$0.47 / ~$2.37
  • 256K context
  • Text, Image, Video input
  • Deep thinking

seed-2-0-lite-260228

Reasoning · Speedbyteplus/seed-2-0-lite-260228Cost-efficient Seed 2.0 variant optimised for high-concurrency and latency-sensitive workloads. Supports multimodal input and tool calling at a fraction of the Pro cost.
  • $0.25 / $1
  • 256K context
  • Text, Image, Video input

seed-2-0-mini-260215

Reasoning · Speedbyteplus/seed-2-0-mini-260215Lightweight Seed 2.0 model designed for edge deployments and cost-sensitive scenarios requiring fast responses with minimal resource usage.
  • ~$0.10 / ~$0.40
  • 256K context
  • Text input

​
Seed 1.x

seed-1-8-251228

Reasoning · Speedbyteplus/seed-1-8-251228Advanced multimodal model with deep thinking and strong agent capabilities. Supports text, image, video, and document understanding with structured output (beta) and context caching.
  • $0.25 / $2
  • 256K context
  • 64K max output
  • Text, Image, Video input
  • Deep thinking

seed-1-6-250915

Reasoning · Speedbyteplus/seed-1-6-250915Stable text generation model from the Seed 1.x series, suited for general-purpose NLP tasks, summarisation, and instruction following.
  • ~$0.25 / ~$2
  • 262K context
  • Text input

​
Third-party (Ark)

kimi-k2-250905

Reasoning · Speedbyteplus/kimi-k2-250905Moonshot Kimi K2 agentic model on BytePlus ModelArk for tool calling and autonomous tasks.
Activation required — enable in the Ark Console before first use.
  • ~$0.50 / ~$2
  • 256K context
  • Text input

kimi-k2-thinking-251104

Reasoning · Speedbyteplus/kimi-k2-thinking-251104Moonshot Kimi K2 thinking variant on BytePlus ModelArk with chain-of-thought reasoning and tool use.
Activation required — enable in the Ark Console before first use.
  • ~$0.60 / ~$2.50
  • 256K context
  • Text input
  • Thinking

deepseek-v4-pro-260425

Reasoning · Speedbyteplus/deepseek-v4-pro-260425DeepSeek V4 Pro on BytePlus ModelArk: frontier open MoE for coding, reasoning, and long-context agent workloads.
Activation required — enable in the Ark Console before first use.
  • ~$0.47 / ~$2.37
  • 256K context
  • Text input

deepseek-v4-flash-260425

Reasoning · Speedbyteplus/deepseek-v4-flash-260425Cost-efficient DeepSeek V4 Flash on BytePlus ModelArk for fast reasoning and agent workloads.
Activation required — enable in the Ark Console before first use.
  • ~$0.25 / ~$1
  • 256K context
  • Text input

deepseek-v3-2-251201

Reasoning · Speedbyteplus/deepseek-v3-2-251201DeepSeek V3.2 on BytePlus ModelArk with improved reasoning and tool use over V3.1.
  • ~$0.25 / ~$1
  • 256K context
  • Text input

deepseek-r1-250528

Reasoning · Speedbyteplus/deepseek-r1-250528DeepSeek R1 reasoning model on BytePlus ModelArk (May 2025 checkpoint).
Activation required — enable in the Ark Console before first use.
  • ~$0.50 / ~$2
  • 256K context
  • Text input
  • Thinking

gpt-oss-120b-250805

Reasoning · Speedbyteplus/gpt-oss-120b-250805OpenAI GPT OSS 120B on BytePlus ModelArk. Apache 2.0.
  • ~$0.15 / ~$0.60
  • 128K context
  • Text input

glm-4-7-251222

Reasoning · Speedbyteplus/glm-4-7-251222Zhipu GLM-4.7 on BytePlus ModelArk for coding, reasoning, and agentic tasks.
  • ~$0.25 / ~$1
  • 128K context
  • Text input

seed-2-0-code-preview-260328

Reasoning · Speedbyteplus/seed-2-0-code-preview-260328Seed 2.0 code-specialized preview on BytePlus ModelArk for agentic coding workloads.
Activation required — enable in the Ark Console before first use.
  • ~$0.25 / ~$1
  • 256K context
  • Text input