Repository navigation
OpenCode Go: gpt-5.6-luna still returns HTTP 500 'Internal server error' (confirmed 2026-09-07) #47778
Description
Summary
gpt-5.6-luna on the OpenCode Go plan still returns HTTP 500 {"type":"error","error":{"type":"error","message":"Internal server error"}} for every request. Confirmed live on 2026-09-07 with a working Go subscription and the same API key that succeeds on other catalog models. This duplicates earlier reports (#47463, #43565) - still unfixed, adding a fresh data point with a control test.
Reproduction (2026-09-07, plan: OpenCode Go subscription)
curl -sS -o /dev/null -w "%{http_code}\n" \
-H "Authorization: Bearer $OPENCODE_GO_API_KEY" \
-H "x-opencode-session: $(uuidgen)" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.6-luna","messages":[{"role":"user","content":"Reply with exactly: pong"}],"max_tokens":64}' \
https://opencode.ai/zen/go/v1/chat/completionsResult: 500 with body
{"type":"error","error":{"type":"error","message":"Internal server error"}}Control test (same key, same session, same endpoint)
# model: deepseek-v4-proResult: 200 with normal completion (content: "pong", finish_reason: "stop").
The same single key succeeds on other models (e.g. deepseek-v4-pro), so this is not an auth or billing issue - the model is listed in the catalog but not wired on the Go router.
Expected behavior
gpt-5.6-luna either works on the Go plan like other catalog models, or is removed/marked unavailable in the catalog so subscribers cannot select a model that always fails.
Context
- Follow-up of OpenCode Go: 10 of 35 cataloged models return persistent errors on /v1 endpoint (500s, oa-compat format, upstream not serving) #47463 (Bucket 1: gateway 500s) and gpt-5.6-luna returns empty response / 403 error with OpenCode Go API #43565 (empty response/403) - both still open.
- Related service stability thread: OpenCode Go service (zen/go/v1) frequent intermittent outages — HTTP 000 / 503 / Cloudflare 524 #36889.
Activity
egorov-maxim commentedon Sep 7, 2026
Additional confirmation (2026-09-07): reproduced with the subscriber's own
OPENCODE_GO_API_KEYfromapi-keys.env, same endpoint, fresh session UUID.gpt-5.6-luna-> HTTP 500Internal server errordeepseek-v4-pro(control, same key/session) -> HTTP 200,content: "pong",finish_reason: "stop"Luna is still listed in
/v1/modelsbut every inference request 500s at the gateway.github-actions commentedon Sep 7, 2026
This issue might be a duplicate of existing issues. Please check:
gpt-5.6-lunareturns HTTP 500 Internal server error via /zen/go/v1 endpoint #46124:gpt-5.6-lunareturns HTTP 500 Internal server error via /zen/go/v1 endpoint — same model, same error, same endpoint (filed 2026-09-01)You also reference #47463 and #43565 directly in the issue body. Please consider adding your reproduction data as a comment on #46124 or #47463 rather than opening a new issue.
Tarquinen commentedon Oct 20, 2026
Thanks for the report!
gpt-5.6-lunais served on the/responsesendpoint, not/chat/completions. Each Go model is available on the endpoint listed for it in the Go docs: https://opencode.ai/v2/docs/console/go#endpoints. Closing this issue.— from 𝕺𝖕𝖊𝖓𝕮𝖔𝖉𝖊