SYLIN
Language & code models   WK 47 / 2026   Updated Nov 19   1 min read

A very cheap multimodal agent model, and the weights are out

Hy4 Flash costs $0.07 per million input tokens. The 441 GB weights are for big rigs only.

CHEAP AND OPEN

Hy Flash read an invoice image and wrote the right row into SQLite in about 30 seconds, flagging oddities instead of guessing. It is Tencent's cheap multimodal model, and this week it published its weights.

The short version
Good atcheap image-plus-text agent work with a 1M-token context. 224B parameters, 12B active per token.
To try itAPI at $0.07 in and $0.28 out per million tokens. Weights are on Hugging Face and GitHub.
The catch441 GB of weights, so most people will use the API. Hands-on runs were slow: 13 minutes for a file-sorting task.

The deeper look

Plotly tested it on a data-analytics bench and reports it beat GPT Luna while costing $0.13 for 43 questions. That is a vendor-run benchmark from a third party with a product stake, so read it as encouraging, not settled.

The hands-on evidence is Fahd Mirza's, and it is mixed in a useful way. The invoice job took 30 seconds and a three-minute multilingual cafe page rendered Chinese, Hindi and Arabic properly. But sorting nine messy files by computer use took about 13 minutes, though correctly.

Sources disagree on size. Tencent says 12B active; a Hacker News comment said about 64B, likely mixing in the 64B n-gram embedding table that ships with the weights. Trust Tencent's model card here.

It is for builders who run many cheap calls over documents and screenshots. Skip it for latency-sensitive work, and do not plan on running it locally without a multi-GPU server.

How to start: the API docs are at hy.tencent.ai/research/hy4-flash. Weights: huggingface.co/tencent/Hy4-flash. Community quantizations exist if you have the memory.

How to start
With Ollama
$ ollama run hf.co/AngelSlim/Hy4-flash-GGUF
With llama.cpp
$ llama-server -hf AngelSlim/Hy4-flash-GGUF
With vLLM
$ vllm serve tencent/Hy4-flash
Download the weights
$ hf download tencent/Hy4-flash
Via API (OpenRouter)
$ curl https://openrouter.ai/api/v1/chat/completions -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{"model": "tencent/hy4-flash", "messages": [{"role": "user", "content": "Hello"}]}'

More this week5 stories