wylon - Token Factory

Three capabilities, one integration

Choose by task without rebuilding account, authentication, and billing flows for every modality.

Chat and agentsLive

Complex tasks, long context, and agent workflows

For enterprise knowledge, customer service, coding, and systems work, with streaming, tool calls, and conversational context caching.

GLM-5.3 DeepSeek-V4-Flash

API compatibilityOpenAI / Anthropic

BillingPer token

Image generation and editingLive

Campaign assets, rendered text, and guided edits

Multiple aspect ratios, 2K output, and multi-reference editing.

Qwen-Image-2512 SenseNova-U1.5-8B-MoT

API compatibilityOpenAI Images

BillingPer image

Video generationLive

Product demos, short-form content, and complex motion

480p and 720p output with a fixed five-second duration.

Wan2.2-T2V-A14B

Request formatVolcengine Ark API compatible

BillingPer second

Domestic inference infrastructure for production

Every capability runs on domestic GPUs and the wylon super-node architecture.

01

Domestic GPU support

Kernels, scheduling, and parallel strategies are tuned across multiple domestic GPU architectures.

02

Super-node architecture

High-bandwidth interconnects and topology-aware scheduling support demanding concurrent inference workloads.

03

Chat context caching

Reuse system prompts, retrieved context, tool definitions, and conversations to reduce repeated token cost.

Keep the API patterns you already use

Each capability follows its corresponding mainstream interface to reduce migration work.

One key, three request types

Use the same account and API key, then replace the service URL and model ID in your existing client.

Chat → OpenAI / Anthropic compatible
Image → OpenAI Images compatible
Video → Volcengine Ark video API request format

# pip install openai
                from openai import OpenAI

                client = OpenAI(
                base_url="https://api.wylon.cn/v1",
                api_key="wyl_...",
                )

                resp = client.chat.completions.create(
                model="ZhipuAI/GLM-5.3",
                messages=[{"role": "user",
                "content": "Hello, wylon."}],
                stream=True,
                )

                for chunk in resp:
                print(chunk.choices[0].delta.content, end="")
              

# pip install openai
                from openai import OpenAI

                client = OpenAI(
                base_url="https://api.wylon.cn/v1",
                api_key="wyl_...",
                )

                image = client.images.generate(
                model="Qwen-Image-2512",
                prompt="A futuristic cloud computing center",
                size="1024x1024",
                )

                print(image.data[0].url)
              

# Volcengine Ark video API-compatible request body
                {
                "model": "Wan2.2-T2V-A14B",
                "content": [
                {
                "type": "text",
                "text": "A product slowly rotates through soft light"
                }
                ],
                "resolution": "720p",
                "duration": 5
                }
                # See the API docs for task submission and status polling

From first request to enterprise deployment

One account

One API key and a unified usage system

Three capabilities

Chat, image, and video generation are live

Visible usage

Clear billing by token, image, or video duration

Enterprise access

Model allowlists, dedicated plans, and deployment support

FAQ

Which models are supported?

Live models include GLM-5.3, DeepSeek-V4-Flash, Qwen-Image-2512, SenseNova-U1.5-8B-MoT, and Wan2.2-T2V-A14B. See the model catalog for capabilities and pricing.

Which APIs are compatible?

Chat supports OpenAI and Anthropic compatibility, image supports OpenAI Images, and video uses a Volcengine Ark video API-compatible request format. Refer to the API docs for exact fields and endpoints.

Do you offer enterprise services?

Yes. We offer dedicated plans for enterprise customers. Reach out via Contact us to talk to our solutions team.

How does wylon handle my data?

wylon handles your data in accordance with applicable regulations. We do not use your data to train models or for unrelated commercial purposes. You can request deletion at any time. Details: Privacy Policy.

What if the model I need is not listed?

We continuously expand the curated catalog. Enterprise customers can contact us for model allowlisting, custom onboarding, or dedicated deployment.

One entry point for three generative capabilities