Hy3
By Tencent. 298.8 billion parameters, a context window of 262,144 tokens and the licence apache-2.0.
Facts
- Released
- 2026-07-02 the day the repository was first published on Hugging Face Hugging Face, read
- Licence
- apache-2.0 the licence the model card declares Hugging Face, read
- Open weights
- Yes the weights are published in this Hugging Face repository Hugging Face, read
- Parameters
- 298.8 billion counted from the safetensors weight files Hugging Face, read
- Active parameters
- 24.4 billion estimate estimated from the expert counts and sizes in the configuration model configuration, read
- Knowledge cutoff
- Unknown
- Context window
- 262,144 tokens the maximum position embeddings in the model configuration model configuration, read
- 262,144 tokens the context length OpenRouter lists OpenRouter, read
- Longest output
- 128,000 tokens the largest output OpenRouter's first provider allows OpenRouter, read
- Tool calling
- Yes OpenRouter lists tools among the supported parameters OpenRouter, read
- Structured output
- Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read
- Reasoning controls
- Yes OpenRouter lists reasoning controls, with the efforts high, low, none OpenRouter, read
- Inputs and outputs
- text in, text out Hugging Face, read
- Good for
- Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read
Prices
| Provider | Input | Output | Context | As of | Source |
|---|---|---|---|---|---|
| NanoGPT direct | 0.066 USD | 0.260 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Kilo Gateway direct | 0.083 USD | 0.330 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| OpenRouter direct | 0.083 USD | 0.330 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Tencent through OpenRouter | 0.083 USD | 0.330 USD | 262,144 | OpenRouter endpoints, read | |
| Deep Infra direct | 0.130 USD | 0.530 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| DeepInfra through OpenRouter | 0.130 USD | 0.530 USD | 262,144 | OpenRouter endpoints, read | |
| LLM Gateway direct | 0.132 USD | 0.528 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| SiliconFlow direct | 0.132 USD | 0.528 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| GMICloud through OpenRouter | 0.140 USD | 0.580 USD | 262,144 | OpenRouter endpoints, read | |
| Hugging Face direct | 0.140 USD | 0.580 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Novita through OpenRouter | 0.140 USD | 0.580 USD | 262,144 | OpenRouter endpoints, read | |
| Vercel AI Gateway direct | 0.140 USD | 0.580 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| Phala through OpenRouter | 0.150 USD | 0.640 USD | 262,144 | OpenRouter endpoints, read | |
| CrossModel direct | 0.160 USD | 0.640 USD | 262,144 | older than 30 days; check the provider | models.dev, read |
| OrcaRouter direct | 0.180 USD | 0.590 USD | 256,000 | older than 30 days; check the provider | models.dev, read |
| AtlasCloud through OpenRouter | 0.200 USD | 0.800 USD | 262,144 | OpenRouter endpoints, read |
Run it on your own hardware
Weights are the sizes of the files a source lists, or an estimate from the parameter count where none does. Memory is an estimate: weights plus KV cache plus 512 MiB and 5 percent of the weights for runtime buffers. Check it against your hardware.
| Quantization | Weights | Memory at 8,192 tokens | Memory at 32,768 tokens |
|---|---|---|---|
| F16 estimate | 557 GiB | 587 GiB | 595 GiB |
| Q8_0 estimate | 296 GiB | 313 GiB | 321 GiB |
| Q4_0 estimate | 157 GiB | 167 GiB | 175 GiB |
Start it with a local runtime
Use it from your harness
Set up for CrossModel with the model tencent/hy3. Each endpoint page has the same setup for its own address.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"crossmodel": {
"npm": "@ai-sdk/openai-compatible",
"name": "CrossModel",
"options": {
"baseURL": "https://api.crossmodel.ai/v1",
"apiKey": "{env:CROSSMODEL_API_KEY}"
},
"models": {
"tencent/hy3": {
"name": "Hy3",
"limit": {
"context": 262144,
"output": 128000
}
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"crossmodel": {
"baseUrl": "https://api.crossmodel.ai/v1",
"api": "openai-completions",
"apiKey": "$CROSSMODEL_API_KEY",
"models": [
{
"id": "tencent/hy3"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Codex speaks only the Responses API, and CrossModel documents no Responses address. A gateway that offers one can sit in between.
- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and CrossModel documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Other ways to reach it
- DeepInfra, model
tencent/Hy3 - Hugging Face, model
tencent/Hy3 - Kilo Gateway, model
tencent/hy3 - LLM Gateway, model
tencent/hy3 - NanoGPT, model
tencent/hy3 - OpenRouter, model
tencent/hy3 - OrcaRouter, model
tencent/hy3 - SiliconFlow, model
tencent/Hy3
Published results
These are results other people published. Baltor did not run them and does not rank models by them.
- Results the maker published on the model card published by tencent Hugging Face, read
Sources of this page
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.