Baltor Get started

Models

Hy-MT2-7B

By Tencent. 8.0 billion parameters, a context window of 8,192 tokens and the licence apache-2.0.

Facts

Released
2026-05-11 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
8.0 billion counted from the safetensors weight files Hugging Face, read
Active parameters
Unknown
Knowledge cutoff
Unknown
Context window
  • 8,192 tokens the context length OpenRouter lists OpenRouter, read
Longest output
  • 4,096 tokens the largest output OpenRouter's first provider allows OpenRouter, read
Tool calling
  • No OpenRouter does not list tools among the supported parameters OpenRouter, read
Structured output
  • Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read
Reasoning controls
Unknown
Inputs and outputs
text in, text out OpenRouter, read
Good for
No source names a use.

Prices

Prices in US dollars per million tokens, as each source lists them
ProviderInputOutputContextAs ofSource
Kilo Gateway direct0.074 USD0.295 USD8,192 older than 30 days; check the providermodels.dev, read
OpenRouter direct0.074 USD0.295 USD8,192 older than 30 days; check the providermodels.dev, read
Tencent through OpenRouter0.074 USD0.295 USD8,192OpenRouter 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 estimate15.0 GiBUnknown: no KV cache numbersBeyond its context
Q8_0 estimate7.9 GiBUnknown: no KV cache numbersBeyond its context
Q4_0 estimate4.2 GiBUnknown: no KV cache numbersBeyond its context

Start it with a local runtime

  • vLLM
    vllm serve tencent/Hy-MT2-7B
  • SGLang
    sglang serve --model-path tencent/Hy-MT2-7B --port 30000

Use it from your harness

Set up for Kilo Gateway with the model tencent/hy-mt2-7b. 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": {
    "kilo": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Kilo Gateway",
      "options": {
        "baseURL": "https://api.kilo.ai/api/gateway",
        "apiKey": "{env:KILO_API_KEY}"
      },
      "models": {
        "tencent/hy-mt2-7b": {
          "name": "Hy-MT2-7B",
          "limit": {
            "context": 8192,
            "output": 4096
          }
        }
      }
    }
  }
}
  • 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": {
    "kilo": {
      "baseUrl": "https://api.kilo.ai/api/gateway",
      "api": "openai-completions",
      "apiKey": "$KILO_API_KEY",
      "models": [
        {
          "id": "tencent/hy-mt2-7b"
        }
      ]
    }
  }
}
  • The apiKey field can name an environment variable as $NAME.

From Pi documentation, read .

Codex

Codex speaks only the Responses API, and Kilo Gateway 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 Kilo Gateway 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.