Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix NVIDIA models with `nvidia/` prefix in model ID fail with 404 [2 comments, 3 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#49369•Fetched 2026-04-08 00:55:57
View on GitHub
Comments
2
Participants
3
Timeline
3
Reactions
0
Author
luoyejiaoe-sourceluoyejiaoe-source
Participants
luoyejiaoe-sourceluoyejiaoe-sourcepacioxpacioxRyceRyce
Timeline (top)
commented ×2cross-referenced ×1

Code Example

# Works ✅
curl https://integrate.api.nvidia.com/v1/chat/completions \
  -d '{"model": "nvidia/nemotron-3-super-120b-a12b", ...}'

# Fails ❌
curl https://integrate.api.nvidia.com/v1/chat/completions \
  -d '{"model": "nemotron-3-super-120b-a12b", ...}'
# Returns: 404 page not found

---

{"model":"nemotron-3-super-120b-a12b","provider":"nvidia","rawErrorPreview":"404 404 page not found"}
RAW_BUFFERClick to expand / collapse

Description

When a model ID contains a prefix that matches the provider name (e.g., nvidia/nemotron-3-super-120b-a12b on NVIDIA provider), OpenClaw incorrectly strips the prefix when making API requests, causing 404 errors.

Steps to reproduce

  1. Add model with ID nvidia/nemotron-3-super-120b-a12b to NVIDIA provider config
  2. Reference it in fallbacks as nvidia/nvidia/nemotron-3-super-120b-a12b
  3. Trigger fallback to this model

Expected behavior

API receives model name: nvidia/nemotron-3-super-120b-a12b

Actual behavior

API receives: nemotron-3-super-120b-a12b → 404 Not Found

Evidence

Direct curl test to NVIDIA API:

# Works ✅
curl https://integrate.api.nvidia.com/v1/chat/completions \
  -d '{"model": "nvidia/nemotron-3-super-120b-a12b", ...}'

# Fails ❌
curl https://integrate.api.nvidia.com/v1/chat/completions \
  -d '{"model": "nemotron-3-super-120b-a12b", ...}'
# Returns: 404 page not found

Log shows OpenClaw sends wrong model name:

{"model":"nemotron-3-super-120b-a12b","provider":"nvidia","rawErrorPreview":"404 404 page not found"}

Other NVIDIA models work fine

  • z-ai/glm5 ✅
  • moonshotai/kimi-k2.5 ✅
  • deepseek-ai/deepseek-v3.2 ✅

Environment

  • OpenClaw version: 2026.3.13
  • Provider: NVIDIA (integrate.api.nvidia.com)

extent analysis

Fix Plan

The fix involves modifying the OpenClaw code to correctly handle model IDs with prefixes matching the provider name.

Step-by-Step Solution

  1. Update the model ID parsing logic: Modify the code that constructs the API request to check if the model ID already includes the provider prefix.
  2. Conditionally append the provider prefix: Only append the provider prefix to the model ID if it doesn't already start with the prefix.

Example code snippet (in Python):

def construct_api_request(model_id, provider):
    # Check if model ID already includes provider prefix
    if not model_id.startswith(provider + "/"):
        # Append provider prefix if not present
        model_id = f"{provider}/{model_id}"
    return {"model": model_id}

# Example usage:
model_id = "nvidia/nemotron-3-super-120b-a12b"
provider = "nvidia"
request_data = construct_api_request(model_id, provider)
print(request_data)  # Output: {"model": "nvidia/nemotron-3-super-120b-a12b"}

Verification

To verify the fix, repeat the steps to reproduce the issue and check the API request logs to ensure the correct model ID is being sent.

Extra Tips

  • Make sure to update the OpenClaw version to include this fix to prevent similar issues in the future.
  • Consider adding test cases to cover different model ID scenarios to prevent regressions.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#installation#tensor shape#autograd error#model save/load#optimization

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix NVIDIA models with `nvidia/` prefix in model ID fail with 404 [2 comments, 3 participants]