Baltor Get started

Models

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

Prices in US dollars per million tokens, as each source lists them
ProviderInputOutputContextAs ofSource
NanoGPT direct0.066 USD0.260 USD262,144 older than 30 days; check the providermodels.dev, read
Kilo Gateway direct0.083 USD0.330 USD262,144 older than 30 days; check the providermodels.dev, read
OpenRouter direct0.083 USD0.330 USD262,144 older than 30 days; check the providermodels.dev, read
Tencent through OpenRouter0.083 USD0.330 USD262,144OpenRouter endpoints, read
Deep Infra direct0.130 USD0.530 USD262,144 older than 30 days; check the providermodels.dev, read
DeepInfra through OpenRouter0.130 USD0.530 USD262,144OpenRouter endpoints, read
LLM Gateway direct0.132 USD0.528 USD262,144 older than 30 days; check the providermodels.dev, read
SiliconFlow direct0.132 USD0.528 USD262,144 older than 30 days; check the providermodels.dev, read
GMICloud through OpenRouter0.140 USD0.580 USD262,144OpenRouter endpoints, read
Hugging Face direct0.140 USD0.580 USD262,144 older than 30 days; check the providermodels.dev, read
Novita through OpenRouter0.140 USD0.580 USD262,144OpenRouter endpoints, read
Vercel AI Gateway direct0.140 USD0.580 USD262,144 older than 30 days; check the providermodels.dev, read
Phala through OpenRouter0.150 USD0.640 USD262,144OpenRouter endpoints, read
CrossModel direct0.160 USD0.640 USD262,144 older than 30 days; check the providermodels.dev, read
OrcaRouter direct0.180 USD0.590 USD256,000 older than 30 days; check the providermodels.dev, read
AtlasCloud through OpenRouter0.200 USD0.800 USD262,144OpenRouter 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.

QuantizationWeightsMemory at 8,192 tokensMemory at 32,768 tokens
F16 estimate557 GiB587 GiB595 GiB
Q8_0 estimate296 GiB313 GiB321 GiB
Q4_0 estimate157 GiB167 GiB175 GiB

Start it with a local runtime

  • vLLM
    vllm serve tencent/Hy3
  • SGLang
    sglang serve --model-path tencent/Hy3 --port 30000

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

Published results

These are results other people published. Baltor did not run them and does not rank models by them.