Zen: gpt-5.6-luna / gpt-5.6-terra fail with "Error from provider (Console): Upstream request failed" #39831

Activity

1. github-actions

   assigned

   MrMushrooooom

   on Jul 31, 2026
2. github-actions commented on Jul 31, 2026

   

   github-actionsBot

   on Jul 31, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • OpenCode Zen lists GPT 5.6 Terra but cannot run it #38624: OpenCode Zen lists GPT 5.6 Terra but cannot run it (same model, same Zen provider failure)
   • All paid OpenCode Zen models fail with 'Upstream request failed' — free models work #36506: All paid OpenCode Zen models fail with 'Upstream request failed' — free models work (same error pattern across Zen paid models)
   • ZEN gemini-3.6-flash returns "Upstream request failed" while gemini-3.5-flash works #39293: ZEN gemini-3.6-flash returns "Upstream request failed" (same error string you referenced, different model)
3. ltceu6o5fu commented on Jul 31, 2026

   

   ltceu6o5fu

   on Jul 31, 2026

   More actions

   I am also experiencing the same issue. When making an API request using the curl command, the server returns an invalid_prompt error indicating an upstream request failure.

   To Reproduce
   Send a request to the API using curl.
   Target the gpt-5.6-luna model.
   Expected behavior
   The request should be processed successfully and return a valid response.

   Actual behavior
   The request(https://opencode.ai/zen/go/v1/responses) fails and returns the following JSON error message:

   {"model":"gpt-5.6-luna","error":{"code":"invalid_prompt","message":"Error from provider (Console Go): Upstream request failed"}}

   👍React with 👍1Reacted by Rik Svendsen Rose
4. xxxxchaos commented on Aug 2, 2026

   

   xxxxchaos

   on Aug 2, 2026

   More actions

   Reproduced from a Hong Kong production server via the documented Zen API endpoint. Additional comparison details from #40162:

   • gpt-5.6-luna: HTTP 403
   • gpt-5.6-terra: HTTP 403
   • gpt-5.4-mini: HTTP 200 with the same Zen API key and host
   • claude-haiku-4-5: HTTP 200 with the same Zen API key and host
   • Both IPv4 and IPv6 reproduce the GPT-5.6 failure

   The more specific upstream error is:

   Error from provider (Console): Upstream request failed: [unsupported_country_region_territory] Country, region, or territory not supported
   

   This model-level comparison suggests the Zen credential and general connectivity are valid, and the failure is specific to the current GPT-5.6 upstream route rather than all Zen traffic from the host.
5. 1138069580qq-create commented on Aug 7, 2026

   

   1138069580qq-create

   on Aug 7, 2026

   More actions

   Independent reproduction from a Windows 11 Go subscriber:

   • OpenCode Desktop 1.18.15: opencode-go/gpt-5.6-luna fails on a normal prompt with Upstream request failed: [403] This model is not available in your region.
   • OpenCode CLI 1.18.15: the same model and prompt reproduce the same 403, which rules out the Desktop UI layer.
   • Direct connectivity and an explicit local HTTP proxy both reproduce the error; changing the client egress does not change the result.
   • Grok works from the same Go subscription/workspace, so authentication and general Go connectivity are valid.
   • A separate Desktop local-backend CORS issue was fixed locally; the Luna 403 persisted and also reproduces in the CLI.

   This is consistent with a server-side upstream routing or forwarded geographic-header issue, rather than a local installation or proxy configuration problem. It also appears relevant to the still-open PR #40180.

   Could a maintainer confirm:

   1. whether this is an expected Go model availability restriction for affected accounts/regions;
   2. whether fix(zen): strip client IP/geo headers to prevent geoblock #40180 or an equivalent server-side change will be deployed; and
   3. whether the Go model catalog can hide models that will be rejected at invocation time?
6. FractalMind commented on Aug 11, 2026

   

   FractalMind

   on Aug 11, 2026

   More actions

   user@myVPShost~$ opencode --version
   1.18.16
   user@myVPShost~:~$ opencode auth list

   ┌ Credentials ~/.local/share/opencode/auth.json
   │
   ● OpenCode Zen api
   │
   └ 1 credentials

   user@myVPShost~:~$ opencode run --model opencode/gpt-5.6-luna "Reply exactly: OK"

   build · gpt-5.6-luna

   Error: No provider available
   user@myVPShost~:~$ opencode run --model opencode/gpt-5.5 "Reply exactly: OK"

   build · gpt-5.5

   OK
7. geminaldiol2333-commits

   closed this as completedon Aug 19, 2026