Fork with Opus-4.7 / GPT-5.4 / GPT-5.3-codex / GPT-5.4-mini / gemini-3.1-pro / gemini-3-flash support, feedback welcome

[betaHi]

Thanks for building and sharing this project.

I added support for newer Opus, GPT and gemini models in my fork and verified them with Claude Code:

• claude-opus-4.7 with adaptive thinking (low, medium, high, xhigh, max)
• gpt-5.4
• gpt-5.3-codex
• gpt-5.4-mini
• gemini-3.1-pro
• gemini-3-flash

This also covers the max_tokens / max_completion_tokens issue that affects gpt-5.3-codex and gpt-5.4-mini.

You can use it with:

npx betahi-copilot-api@latest start

Example Claude Code config:

{
  "env": {
    "ANTHROPIC_BASE_URL": "http://localhost:4141",
    "ANTHROPIC_AUTH_TOKEN": "dummy",
    "ANTHROPIC_MODEL": "gpt-5.3-codex",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "gpt-5.3-codex",
    "ANTHROPIC_SMALL_FAST_MODEL": "gpt-5.4-mini",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "gpt-5.4-mini",
    "COPILOT_REASONING_EFFORT": "medium",
    "DISABLE_NON_ESSENTIAL_MODEL_CALLS": "1",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"
  }
}

Supported reasoning effort:

• claude-opus-4.7: low, medium, high, xhigh, max
• gpt-5.4: low, medium, high, xhigh
• gpt-5.3-codex: low, medium, high, xhigh
• gpt-5.4-mini: none, low, medium

Repo: https://github.com/betaHi/copilot-api

README: https://github.com/betaHi/copilot-api?tab=readme-ov-file#gpt-and-gemini-support

If anyone tries it, feedback is welcome.

[sup3rgiu]

#233