Repository navigation
Nvidia NIM API hangs for DeepSeek v4 reasoning models without chat_template_kwargs #24264
Description
Description
Description
When using Nvidia NIM's deepseek-ai/deepseek-v4-flash or deepseek-v4-pro reasoning models through OpenCode, the API hangs and never returns a response.
This happens because Nvidia NIM strictly requires chat_template_kwargs: { enable_thinking: true, thinking: true } in the root of the JSON payload to stream reasoning tokens. Because the Vercel AI SDK strips out unknown configurations, attempting to configure this via opencode.jsonc does not work, resulting in an indefinite timeout.
Steps to Reproduce
- Configure OpenCode to use the
nvidiaprovider. - Select
deepseek-ai/deepseek-v4-flashas the active model. - Send a prompt.
- The API connection hangs and eventually times out without a response.
Expected Behavior
OpenCode should correctly inject chat_template_kwargs into the fetch payload when a deepseek-v4 model is active, allowing it to successfully receive and process the reasoning and text streams.
Plugins
No response
OpenCode version
1.14.24
Steps to reproduce
Steps to Reproduce
-
Configure OpenCode to use the Nvidia NIM API by setting up an NVIDIA_API_KEY or configuring the provider in your settings.
-
In opencode.jsonc, ensure that a deepseek-v4 model is configured under the nvidia provider:
"provider": {
"nvidia": {
"models": {
"deepseek-ai/deepseek-v4-flash": {
"limit": { "context": 100000, "input": 70000, "output": 16384 }
}
}
}
} -
Start an OpenCode session and set the active model to nvidia/deepseek-ai/deepseek-v4-flash.
-
Send a simple prompt (e.g., "Reply with exactly: ok").
-
Observe the failure: The OpenCode agent enters a "busy" state and hangs indefinitely.
-
Verify the underlying cause: Run a raw curl command to the Nvidia NIM API without chat_template_kwargs—it will fail to return a response or hang, replicating the
behavior seen in OpenCode.
1 # This hangs/fails, replicating OpenCode's behavior
2 curl https://integrate.api.nvidia.com/v1/chat/completions
3 -H "Authorization: Bearer $NVIDIA_API_KEY"
4 -H "Content-Type: application/json"
5 -d '{ "model": "deepseek-ai/deepseek-v4-flash", "messages": [{"role":"user","content":"Hello World"}], "stream": true }'
Screenshot and/or share link
No response
Operating System
Windows 11
Terminal
No response
Activity
github-actions commentedon Apr 25, 2026
This issue might be a duplicate of existing issues. Please check:
chat_template_kwargsto agents — this issue shares the same root cause (inability to configurechat_template_kwargsthrough OpenCode's config).nakul-krishnakumar commentedon Apr 28, 2026
Having the same issue.
ap-gilang-adrian commentedon Apr 29, 2026
hope its getting resolved soon
RipMrLucas commentedon May 24, 2026
Hm
Still active
fix(provider): inject chat_template_kwargs for NVIDIA DeepSeek V4, fi…
mahad-writes commentedon Jun 26, 2026
I performed additional testing and can confirm this is not an API key or NVIDIA issue.
Verified
nvidia/nemotron-3-ultra-550b-a55bUsing the same API key, same endpoint, and same model, NVIDIA's official Python example (OpenAI SDK) streams successfully.
Using the same API key in OpenCode, the model hangs indefinitely in the Build/Thinking phase.
Other NVIDIA NIM models continue to work correctly.
Since #24264 was caused by
options.extraBodynot being propagated for NVIDIA reasoning models, this may be a related regression or an additional compatibility issue specific to Nemotron 3 Ultra.fehmi commentedon Jun 28, 2026
some models work, some doesn't. deepseek v4 pro and and glm 5.1 are not working for example. they hang forever. no any response. The thing is, same models doesn’t work on vs code too.
CytITDchen commentedon Aug 4, 2026
This happened to multiple models now including minimax M3, GLM 5.2
avanpub commentedon Aug 6, 2026
Hi,
I have an opencode go subscription and everything works fine. I wanted to give a try to nvidia and I confirm that the default connection to nvidia is broken in Opencode (at least, in v1.18.14). The problem seems complex, I tested in plan mode:
avanpub commentedon Aug 7, 2026
Hi, I cloned opencode and used my opencode go subscription with GLM 5.2 (for planning) and deepseek v4 flash (for coding/debugging). I now have local opencode working properly. I unfortunately don't have enough time to go to do a PR and go to official review. I let everybody with a maximum information so that any motivated contributor could transform that. The problem is more subtile:
This is the full explanation (generated by glm) + patch I used locally:
avanpub commentedon Aug 7, 2026
The patch as is: https://pastebin.com/AXTLj3Rg
(didn't find a way to upload it).
fix: NVIDIA NIM model compatibility issues
fix: NVIDIA NIM model compatibility issues
github-actions commentedon Oct 8, 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.
opencode-agent commentedon Oct 8, 2026
Thanks for the detailed report. We looked into this and the diagnosis is likely wrong: the AI SDK does not strip unknown options for this provider. NVIDIA uses
@ai-sdk/openai-compatible, which passes any provider option it doesn't recognize straight through into the request body. We also haven't been able to reproduce the hang.We'd recommend updating to OpenCode V2: https://opencode.ai/v2/docs
V2 has built-in reasoning variants for DeepSeek V4 on NVIDIA that set
chat_template_kwargsfor you:nonesendschat_template_kwargs: { "thinking": false }high/maxsendchat_template_kwargs: { "thinking": true, "reasoning_effort": "<effort>" }To select one:
ctrl+tto cycle through the current model's variants.#<variant>to the model:opencode run --model nvidia/deepseek-ai/deepseek-v4-flash#high "..."provider/model#variantform in itsmodelfield.If you need different kwargs, you can set an arbitrary request
bodyon the provider, model, or variant inopencode.jsonc(see Models → Options):{ "$schema": "https://opencode.ai/config.json", "providers": { "nvidia": { "models": { "deepseek-ai/deepseek-v4-flash": { "body": { "chat_template_kwargs": { "thinking": true } } } } } } }If you still see a hang on V2, please open a new issue with the exact model, the variant you selected, and the V2 version.