Models and prices / hy4-preview

Hunyuan Hy4 Preview 19% off

Preview of the next flagship Hunyuan model for agents and coding, with about 1M tokens of context and tool calls. Preview models may change or be retired.

OpenAI compatibleAnthropic compatible

Pricing

• Send hy4-preview as the model.
• Cached input is the part of a prompt served from the context cache. The struck-through price is the model maker's own price.
• Thinking is billed as output tokens. Set max_tokens to 1000 or more, or the budget may go to thinking alone.

Specs

Call it with the OpenAI API

curl https://api.aifans.fan/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "hy4-preview", "messages": [{"role": "user", "content": "Hello"}], "max_tokens": 1000}'

# pip install openai
from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.aifans.fan/v1")
resp = client.chat.completions.create(
    model="hy4-preview",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=1000,
)
print(resp.choices[0].message.content)

Use it in Claude Code

Put this in ~/.claude/settings.json (Windows: %USERPROFILE%\.claude\settings.json) and start Claude Code.

{
  "env": {
    "ANTHROPIC_BASE_URL": "https://api.aifans.fan",
    "ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
    "ANTHROPIC_MODEL": "hy4-preview",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "hy4-preview",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "hy4-preview",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "hy4-preview",
    "CLAUDE_CODE_SUBAGENT_MODEL": "hy4-preview"
  }
}

More about this model