LiteLLM / LiteLLM

LiteLLM OCI GPT-5 max_completion_tokens Parameter Mapping Error

Fix LiteLLM OCI adapter incorrectly mapping max_completion_tokens to maxTokens for GPT-5 models Includes evidence for LiteLLM troubleshooting demand.

Category
LiteLLM
Error signature
Unsupported parameter: 'max_tokens' is not supported
Quick fix
Compare the failing environment with a known working setup, then change one configuration value at a time.
Updated

What this error means

Unsupported parameter: 'max_tokens' is not supported is a LiteLLM failure pattern reported for developers trying to fix litellm oci adapter incorrectly mapping max_completion_tokens to maxtokens for gpt-5 models. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Bug report (2026-05-07) shows LiteLLM OCI adapter translates max_completion_tokens=100 into legacy camelCase maxTokens, which OCI GPT-5 models reject with ‘Unsupported parameter: max_tokens is not supported’.

Common causes

Quick fixes

  1. Confirm the exact error signature matches Unsupported parameter: 'max_tokens' is not supported.
  2. Check the LiteLLM account, local tool state, and provider configuration involved in the failing workflow.
  3. Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

Step-by-step troubleshooting

  1. Capture the exact error message and the command, editor action, or request that triggered it.
  2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
  3. Review the source evidence below and compare it with your environment.
  4. Apply one change at a time and rerun the smallest failing action.
  5. Keep the working fix documented for the team or deployment environment.

How to prevent it

Sources checked

Evidence note: Bug report (2026-05-07) shows LiteLLM OCI adapter translates max_completion_tokens=100 into legacy camelCase maxTokens, which OCI GPT-5 models reject with ‘Unsupported parameter: max_tokens is not supported’.

FAQ

What should I check first?

Start with the exact Unsupported parameter: 'max_tokens' is not supported text and the smallest action that reproduces it.

Can I ignore this error?

No. Treat it as a failed LiteLLM workflow until the root cause is understood.

Is this guaranteed to have one fix?

No. The imported evidence supports the troubleshooting path above, but tool behavior can vary by account, plan, version, provider, and local configuration.

How do I know the fix worked?

Rerun the same command, editor action, or request. The fix is working when that action completes without Unsupported parameter: 'max_tokens' is not supported.