ByteDance AI API

Seed 2.1 Turbo is the faster, lower-cost variant in ByteDance's Seed 2.1 family, a model line built for coding, long-horizon agent tasks, and multimodal understanding. It accepts text and image input, has a 256K context window, and supports function calling in an OpenAI-compatible format, so existing tool-use pipelines port over with little change. ByteDance positions it for high-volume production workloads such as agent pipelines, coding assistance, and document processing, and prices it at roughly half the cost of Seed 2.1 Pro. The company reports performance close to the Pro version and comparable to GPT-5.5 on coding and agent tasks, though no independently verified benchmark scores for Turbo were published at launch. Choose it when volume and cost drive the decision rather than peak capability; Seed 2.1 Pro remains the stronger option for the hardest tasks.

Seedream 5 Lite is a lighter, faster tier of ByteDance's Seedream 5 image generation line, launched in February 2026. Seedream is ByteDance's flagship text-to-image and editing model family; this specific release is new enough that we did not find independent third-party benchmarks for it yet, so treat capability claims below as ByteDance's own. ByteDance describes it as the first Seedream model with web-connected retrieval, letting it draw on live online information during generation, plus multi-step reasoning and example-based editing, where a before/after reference pair shows the model what transformation to apply instead of describing it in words. It accepts up to 14 reference images and outputs at 2K or 3K resolution with aspect ratio control from 1:1 to 21:9, which fits editing work defined by example rather than by prompt alone.

Skylark Pro SC 260215 is a dated snapshot of Skylark Pro, the chat model family ByteDance serves through its BytePlus ModelArk platform. The 260215 identifier corresponds to a February 15, 2026 build. BytePlus positions Skylark Pro as its flagship model for complex question answering, summarization, creative writing, and role-playing. The model line also supports function calling and structured output through the API. This snapshot has a 128,000-token context window and returns up to 12,000 output tokens per response. Pinning a dated snapshot like this one keeps behavior stable across requests, which is useful when a workload has been tuned against a specific build rather than a rolling alias.

Seed 2.0 Code is ByteDance's dedicated coding model, released with the Seed 2.0 family in February 2026. It is built for agentic software work rather than autocomplete, with a stated focus on decomposing tasks into plans and revising those plans as work progresses, which suits multi-step feature implementation and bug diagnosis and repair. The model accepts image input alongside text, so it can read design mockups, screenshots, and charts and generate code from them. ByteDance cites high-precision text extraction and chart understanding as part of its multimodal perception. It has a 256K context window and up to 128K output tokens. ByteDance has not published benchmark scores for the Code variant. The same model powers coding in TRAE, ByteDance's AI IDE.

Seed 2.0 Pro is the flagship model in ByteDance's Seed 2.0 series, built for long-chain reasoning, coding, and agent workflows. It accepts text, image, and video input and returns text. On benchmarks it scores 98.3 on AIME 2025, 87.8 on LiveCodeBench v6, and 76.5% on SWE-Bench Verified, with a Codeforces rating of 3020. For agent tasks it reaches 90.4 on tau2-Bench Retail and 77.3 on BrowseComp, and it ranks sixth on the LMArena leaderboard alongside GPT-5.2, Claude Opus 4.5, and Gemini 3 Pro. At $0.50 per million input tokens and $3 per million output tokens with a 256K context window, it is priced well below the frontier models it competes with, a fit for coding agents and complex multi-step workflows.

Seedream 4.5 is ByteDance's text-to-image and image-editing model, released in December 2025 as the follow-up to Seedream 4.0. It renders at 1K, 2K, and 4K resolution across multiple aspect ratios, can return up to 10 images per request, and accepts up to 14 reference images for multi-image editing. ByteDance says it improves on Seedream 4.0 in editing consistency, including better preservation of subject details, lighting, and color tone, along with sharper portrait refinement and small-text rendering. That makes it suited to tasks like product swaps, text overlay copying, and element repositioning across a reference set rather than a single one-off generation. It has placed on the Arena text-to-image leaderboard, an independent crowdsourced ranking of image models.

Seed 1.8 is an agentic multimodal model from ByteDance's Seed team that combines search, code, and GUI agent capabilities in a single system. It accepts text, image, and video input and supports three thinking modes that adjust reasoning depth to task complexity. ByteDance reports 67.6 on BrowseComp-en for web search tasks and 87.8 on VideoMME for long-form video understanding, and says the model approaches Gemini 3 Pro on most multimodal tasks while surpassing it on BrowseComp-en. With a 256K context window and tool calling, it fits multi-step agent workflows such as web research, code generation, and GUI automation over screenshots.

UI-TARS 1.5 7B is a multimodal vision-language agent by ByteDance optimized for GUI automation across desktop, web, mobile, and game environments. It uses reinforcement learning-based reasoning to plan and execute actions on graphical interfaces. The model achieves state-of-the-art results on benchmarks like OSWorld, WebVoyager, and AndroidWorld.

Seedance 1.0 Lite is ByteDance's speed-optimized AI video generation model that creates 5 second videos at 480p-720p resolution from text prompts or images. It supports text-to-video and image-to-video generation with smooth motion and multi-shot narrative capabilities, designed for fast iteration and experimentation.

Seedance 1.0 Pro is ByteDance's professional-grade AI video generation model that produces cinematic 1080p videos from text or images. It excels at multi-shot storytelling with consistent subjects and visual style across scenes, featuring smooth motion, rich details, and advanced prompt following for production-quality content.

Skylark Pro SC 250615 is a June 2025 snapshot of Skylark Pro, ByteDance's flagship chat model line offered through its BytePlus ModelArk platform. Skylark was ByteDance's original large language model family, made commercially available in 2023, and is the international counterpart to the Doubao models. BytePlus positions Skylark Pro for complex question answering, summarization, creative writing, and role-play, and publishes a role creation guide for building persona-driven and multi-character chat. Role-play platforms such as Moescape have adopted it as a character chat model. The model has a 128,000-token context window, and this deployment supports up to 12,000 output tokens per response. BytePlus documentation lists function calling and structured output among the Skylark Pro line's capabilities, with pricing of $0.40 per million input tokens and $1.60 per million output tokens.

SDXL Lightning is ByteDance's distilled version of Stability AI's Stable Diffusion XL, built to produce high-quality 1024px images in as few as 1 to 8 diffusion steps instead of the dozens a standard SDXL run needs. It comes from a progressive adversarial diffusion distillation method described in ByteDance's SDXL-Lightning paper, which first trains on mean squared error loss across many timesteps and then adds an adversarial discriminator to sharpen detail as the step count drops. ByteDance describes the 2-step, 4-step, and 8-step configurations as producing consistently good results, while the 1-step variant is more experimental and less stable. Served here through Cloudflare Workers AI, it suits use cases where generation speed and low latency matter more than squeezing out the highest possible fidelity, such as rapid prototyping or applications generating many images per request.