AI Models
Dola-Seedream Series
Dreamina Seedance 2.0
DeepSeek-V4
Dola-Seed-2.0 Series
GPT-OSS
Kimi K2
GLM-4.7
Solutions
Exclusive BytePlus Authorized Partner15+ AI Models.
One API Key.
OpenAI-compatible · Pay-as-you-go · Zero infrastructure
Access the world's best LLMs, video generators, image models, 3D generation, and embeddings through a single API. No volume restrictions, no enterprise commitments.
Full Model Catalog
Every modality. One key.
LLMs, vision, video generation, image creation, 3D objects, and semantic embeddings — all accessible through a single OpenAI-compatible endpoint.
Seed 2.0 Pro
ByteDance
Deep reasoning, multi-modal, 256K context
256K context
Seed 2.0 Lite
ByteDance
Fast agentic model with full tool-use support
256K context
Seed 2.0 Code
ByteDance
Code generation, refactoring & debugging
256K context
DeepSeek-V4 Pro
DeepSeek
State-of-the-art reasoning with 1M token context
1024K context
DeepSeek-V4 Flash
DeepSeek
Lightning-fast inference, 1M context window
1024K context
GPT-OSS 120B
OpenAI
Open-weight 120B reasoning powerhouse
128K context
GLM-4.7
Zhipu
256K context, function calling, reasoning
256K context
Kimi K2
Moonshot
Top agentic & coding model from Moonshot AI
128K context
Seedance 2.0
ByteDance
4K video generation from text, image or video
Seedance 2.0 Fast
ByteDance
Rapid video synthesis for agile workflows
Seedream 5.0
ByteDance
Photorealistic & creative image generation
Seed3D
ByteDance
Text / image to 3D object generation
Multimodal Embedding
ByteDance
Text + image embeddings for semantic search & RAG
Coding Models
AI built for developers — code faster.
Six specialized coding models in one API. Write, debug, refactor, and generate entire codebases using the same OpenAI-compatible interface you already know.
Seed 2.0 Code
Code gen & debugging
GPT-OSS 120B
120B open-weight reasoning
DeepSeek-V4 Pro
1M context • 384K output
DeepSeek-V4 Flash
Fastest DeepSeek inference
GLM-4.7
Deep reasoning + tool use
Kimi K2
Agentic coding workflows
import OpenAI from "openai"const client = new OpenAI({ baseURL: "https://api.untrigin.com/v1/proxy", apiKey: process.env.UNTRIGIN_API_KEY,})const res = await client.chat.completions.create({ model: "seed-2-0-code-preview-260328", messages: [{ role: "user", content: "Refactor this to async/await" }],})console.log(res.choices[0].message.content)Video Generation
Seedance 2.0 — 4K video via API.
Generate, edit, and extend footage from text, images, or existing video clips. Audio-visual synchronization. Up to 1080P @ 24fps. Available now with pay-per-generation pricing.
Resolution
1080P @ 24fps
Pricing
Per generation
Input modes
Text · Image · Video
Untrigin AI Chat — one interface for all models.
Switch between Seed 2.0, DeepSeek-V4, GPT-OSS 120B, and every model in our catalog — no separate accounts, no API keys per provider. One chat, all AI.
Launching soon
Why Untrigin
The simplest way to access frontier AI.
One API Key
A single credential unlocks every model: LLMs, image generation, video, 3D, and embeddings. No juggling multiple provider accounts.
OpenAI-Compatible
Drop our base URL into any OpenAI SDK call. Zero migration cost — your existing code works unchanged with 15+ new models.
Zero Infrastructure
No GPU setup, no model hosting, no quotas to negotiate. Pay only for what you call. Start in seconds, scale without limits.
Start building with 15+ AI models today.
One API key. No commitments. Pay only for what you use.