Repository navigation
Why do I often face "Streaming response failed" when using free Nemotron 3 Ultra in OpenCode Zen? #38051
Description
Description
What happened?
When using the free Nemotron 3 Ultra model provided by OpenCode Zen (via the built-in model list, NOT configured with my own NVIDIA API key), the streaming response frequently fails in the middle of a task. This happens almost every time, especially when the task involves multiple tool calls or generates longer outputs.
The error message appears as:
"Streaming response failed"
After the failure, I have to manually type "continue" or "继续" to resume, but sometimes the model repeats already-generated content, which wastes tokens and time.
What did you expect?
I expected the streaming response to complete without interruption, or at least have automatic retry/resume mechanism built into the free tier.
Steps to reproduce
- Open OpenCode (using the desktop app, not CLI)
- Select the free
Nemotron 3 Ultramodel from the OpenCode Zen model list - Give it a moderately complex task, e.g.:
- "Analyze the structure of my project and suggest improvements"
- Or any task that requires multiple file reads or code generation
- Wait for the response — at some point,
Streaming response failedappears - The session is interrupted; I have to manually type "continue" to resume
Plugins I'm using
opencode-auto-resume(installed via npm, but it doesn't seem to prevent or recover from this specific failure)- No other custom plugins
OpenCode version
- The latest stable desktop version (downloaded from opencode.ai)
Additional context
- I do NOT have my own NVIDIA API key configured — I'm relying purely on the free OpenCode Zen offering.
- I've seen discussions in the community suggesting that the
thinkingparameter might cause compatibility issues with NVIDIA's API. However, since I'm using the OpenCode Zen gateway, I don't have access to modify the request parameters directly. - The frequent interruptions make the model almost unusable for production or serious development work.
Suggestion
Could the OpenCode Zen gateway be updated to:
- Handle the
thinkingparameter compatibility issue with NVIDIA models, OR - Implement automatic retry/reconnection logic for streaming failures on free models?
Thank you for your great work on OpenCode! 🙏
Plugins
opencode-auto-resume
OpenCode version
v1.18.3
Steps to reproduce
No response
Screenshot and/or share link
Operating System
macOS 26.5.2
Terminal
No response
Activity
github-actions commentedon Jul 21, 2026
This issue might be a duplicate of existing issues. Please check:
positiveprogrammer commentedon Jul 22, 2026
This looks an NVIDIA compatibility issue. Their /v1/chat/completions endpoint (nemotron-3-ultra-free) intermittently errors on stream_options: { "include_usage": true }. Stripping the field fixes it.
Adding NVIDIA to a blocklist in the Zen API gateway's modifyBody until NVIDIA resolves it on their end could be temporal fix.
Repro:
curl -X POST https://integrate.api.nvidia.com/v1/chat/completions
-H "Authorization: Bearer $NVIDIA_API_KEY"
-H "Content-Type: application/json"
-d '{
"model": "nvidia/nemotron-3-ultra-550b-a55b",
"messages": [{"role": "user", "content": "hi"}],
"stream": true,
"stream_options": {"include_usage": true}
}'
Run it a few times — server_error appears intermittently. Remove stream_options and it works consistently.
CytITDchen commentedon Jul 28, 2026
Not only desktop, I also got this error in CLO, which means that if OpenCode zen using NVIDIA NIM free endpoint, than it would just be the NVIDIA build api format error(this error commonly occurs when using NVIDIA NIM models on OpenCode)
github-actions commentedon Sep 27, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.