Skip to main content
NewSeedance 2.5 is live→
ModelRunner
Model creator on ModelRunner
Tencent logo

Tencent

tencent

Tencent's 3 models on ModelRunner span Text-to-Image and Image-to-Image, from $0.09 per megapixel upward.

3 public models — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.

Tencent models & pricing

HunyuanImage 3.0 Instruct

HunyuanImage 3.0 Instruct

tencent

Edit and transform an existing image from a written instruction and up to 3 reference images, with an instruction-tuned checkpoint built for following long, complex edit directions.

$0.09 per megapixelimageimageedit
HunyuanImage 3.0 Instruct

HunyuanImage 3.0 Instruct

tencent

Generate high-resolution images from a text prompt with the instruction-tuned HunyuanImage 3.0 checkpoint, built for following long, complex, multi-part descriptions closely.

$0.09 per megapixeltextimage
HunyuanImage 3.0

HunyuanImage 3.0

tencent

Generate high-resolution images from a text prompt with an 80-billion-parameter model built for strong prompt adherence and long, detailed descriptions.

$0.1 per megapixeltextimage

What you can build with Tencent models

Browse by capability

Call a Tencent model in one request

Every endpoint shares the same lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.

cURL

curl -X POST https://queue.modelrunner.run/tencent/hunyuan-image/v3/instruct/edit \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "prompt": "..." }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

Use Tencent models from Claude & Cursor

Connect the ModelRunner MCP server once and your AI assistant can run every Tencent model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Frequently asked questions

What Tencent models can I run on ModelRunner?

The catalog has 3 public Tencent models: HunyuanImage 3.0 Instruct, HunyuanImage 3.0 Instruct and HunyuanImage 3.0. They cover text-to-image and image-to-image. Each one has its own page with a free playground, the full input schema, and copy-paste code.

How much do Tencent models cost?

Pay-per-use, with no subscription: the 3 Tencent models billed per megapixel start at $0.09, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.

How do I call a Tencent model from the API?

POST to https://queue.modelrunner.run/tencent/hunyuan-image/v3/instruct/edit with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.

Can I run Tencent models from Claude or Cursor?

Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and all 3 Tencent models become tools your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.

More on ModelRunner

Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.

Other creators in text-to-image