anomalyco / anomalyco/opencode

gpt-5.6-luna 经 OpenCode Go 中继访问返回 403: "This model is not available in your region"

Open
#41,518 8 comments 0 reactions 1 assignee View on GitHub

@fwang is already working on this.

Since Aug 10, 2026.

Dominant language
TypeScript
Stars
209k
Forks
27.5k
PR merge metrics
PR metrics pending

Description

Description

通过 opencode.ai 的 "OpenCode Go" 中继访问模型 gpt-5.6-luna 时,返回 403。

完整报错:

CC Switch local proxy failed while handling Codex endpoint /responses.
Provider: OpenCode Go; model: gpt-5.6-luna; upstream_status: HTTP 403;
cause: 上游错误 (403):, url: http://127.0.0.1:15721/v1/responses

用有效 Key 直接请求上游验证:

  • GET https://opencode.ai/zen/go/v1/models → 200,列表里确实有 gpt-5.6-luna
  • POST https://opencode.ai/zen/go/v1/responses(model: gpt-5.6-luna, input: "hi")→ 403,
    响应体为:
    {"model":"gpt-5.6-luna","error":{"message":"Error from provider (Console Go): Upstream request failed: [403] This model is not available in your region."}}

同一 Key 请求 deepseek-v4-flash → 200 正常;kimi-k2.7-code 也正常。
所以模型名正确、Key 有效,问题在于上游按地区/账号拒绝了 gpt-5.6-luna。

想确认:gpt-5.6-luna 是否支持当前地区?如果不支持,能否开通?

Plugins

未安装第三方插件。配置里只有一个 glm-vision MCP server(本地)。

OpenCode version

1.18.16(opencode --version)

Steps to reproduce

No response

Screenshot and/or share link
  1. 在 Codex(或 OpenCode)中选择模型 gpt-5.6-luna(经 CC Switch 本地代理转发到 opencode.ai "OpenCode Go" 中继,base_url: https://opencode.ai/zen/go/v1)
  2. 发送任意请求
  3. 立即收到 403:This model is not available in your region.
Image
Operating System

Windows 11(Home China,build 26200)

Terminal

Windows Terminal 1.24.11911.0

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.