Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]:Openclaw update to 2026.4.5-2026.4.8 Nvidia Api Switching models triggers an error, [1 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#63029•Fetched 2026-04-09 07:59:21
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
Billxu2019Billxu2019
Participants
Billxu2019Billxu2019
Timeline (top)
labeled ×2

When using version 2026.4.2, models utilizing the NVIDIA API functioned normally; however, after upgrading to version 2026.4.8, some models ceased to work correctly. Furthermore, manually switching models triggers the following error: Failed to set model: GatewayRequestError: model not allowed: stepfun-ai/step-3.5-flash

The section regarding models within the openclaw.json configuration file is defined as follows: "models": { "nvidia/moonshotai/kimi-k2.5": {}, "nvidia/minimaxai/minimax-m2.5": {}, "nvidia/nvidia/nemotron-3-super-120b-a12b": {}, "nvidia/z-ai/glm5": {}, "nvidia/stepfun-ai/step-3.5-flash": {}, "google/gemma-4-31b-it": {}, "google/gemma-4-26b-a4b-it": {} }, "model": { "primary": "/nvidia/nemotron-3-super-120b-a12b", "fallbacks": [ "nvidia/moonshotai/kimi-k2.5", "nvidia/minimaxai/minimax-m2.5", "nvidia/z-ai/glm5", "nvidia/stepfun-ai/step-3.5-flash" ] }

Could you please advise on how to resolve this issue?

Error Message

When using version 2026.4.2, models utilizing the NVIDIA API functioned normally; however, after upgrading to version 2026.4.8, some models ceased to work correctly. Furthermore, manually switching models triggers the following error:

Root Cause

When using version 2026.4.2, models utilizing the NVIDIA API functioned normally; however, after upgrading to version 2026.4.8, some models ceased to work correctly. Furthermore, manually switching models triggers the following error: Failed to set model: GatewayRequestError: model not allowed: stepfun-ai/step-3.5-flash

The section regarding models within the openclaw.json configuration file is defined as follows: "models": { "nvidia/moonshotai/kimi-k2.5": {}, "nvidia/minimaxai/minimax-m2.5": {}, "nvidia/nvidia/nemotron-3-super-120b-a12b": {}, "nvidia/z-ai/glm5": {}, "nvidia/stepfun-ai/step-3.5-flash": {}, "google/gemma-4-31b-it": {}, "google/gemma-4-26b-a4b-it": {} }, "model": { "primary": "/nvidia/nemotron-3-super-120b-a12b", "fallbacks": [ "nvidia/moonshotai/kimi-k2.5", "nvidia/minimaxai/minimax-m2.5", "nvidia/z-ai/glm5", "nvidia/stepfun-ai/step-3.5-flash" ] }

Could you please advise on how to resolve this issue?

RAW_BUFFERClick to expand / collapse

Bug type

Regression (worked before, now fails)

Beta release blocker

No

Summary

When using version 2026.4.2, models utilizing the NVIDIA API functioned normally; however, after upgrading to version 2026.4.8, some models ceased to work correctly. Furthermore, manually switching models triggers the following error: Failed to set model: GatewayRequestError: model not allowed: stepfun-ai/step-3.5-flash

The section regarding models within the openclaw.json configuration file is defined as follows: "models": { "nvidia/moonshotai/kimi-k2.5": {}, "nvidia/minimaxai/minimax-m2.5": {}, "nvidia/nvidia/nemotron-3-super-120b-a12b": {}, "nvidia/z-ai/glm5": {}, "nvidia/stepfun-ai/step-3.5-flash": {}, "google/gemma-4-31b-it": {}, "google/gemma-4-26b-a4b-it": {} }, "model": { "primary": "/nvidia/nemotron-3-super-120b-a12b", "fallbacks": [ "nvidia/moonshotai/kimi-k2.5", "nvidia/minimaxai/minimax-m2.5", "nvidia/z-ai/glm5", "nvidia/stepfun-ai/step-3.5-flash" ] }

Could you please advise on how to resolve this issue?

Steps to reproduce

Manually Select Model

Expected behavior

Failed to set model: GatewayRequestError: model not allowed: moonshotai/kimi-k2.5

Actual behavior

Failed to set model: GatewayRequestError: model not allowed: moonshotai/kimi-k2.5

OpenClaw version

2026.4.8

Operating system

mac os

Install method

npm

Model

moonshotai/kimi-k2.5

Provider / routing chain

nvidia

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

TL;DR

The issue can likely be resolved by adjusting the model configuration in the openclaw.json file to match the expected format.

Guidance

  • Verify that the model names in the openclaw.json file match the expected format, including the provider prefix (e.g., "nvidia/").
  • Check the openclaw.json file for any typos or inconsistencies in the model names.
  • Ensure that the models section in the openclaw.json file includes all the models that are being used, with their correct names and prefixes.
  • Test the configuration by manually selecting a model that is correctly defined in the openclaw.json file.

Example

No code snippet is provided as the issue seems to be related to configuration rather than code.

Notes

The issue may be related to a change in the expected model name format between versions 2026.4.2 and 2026.4.8. The openclaw.json file seems to be correctly configured, but the error message suggests that the model name is not allowed.

Recommendation

Apply workaround: Adjust the model configuration in the openclaw.json file to match the expected format, including the provider prefix (e.g., "nvidia/"). This should resolve the issue until a more permanent fix is available.

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…

FAQ

Expected behavior

Failed to set model: GatewayRequestError: model not allowed: moonshotai/kimi-k2.5

#api#optimization#mixed precision#training loop#device allocation

Still need to ship something?

×6

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

Back to top recommendations

TRENDING