OpenAI 400 Unsupported parameter max_tokens: use max_completion_tokens instead

TL;DR: Reasoning models reject maxtokens outright, and the replacement has a trap: it budgets hidden reasoning tokens too. Send maxcompletiontokens everywhere, size it generously, and recognize the empty-answer signature of a starved budget. Use 'maxcompletiontokens' instead. Send maxcompletiontokens everywhere, never maxtokens.

The symptom

400 Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead. Fires on o-series and GPT-5 reasoning models. Code that worked on GPT-4o breaks the moment it points at a reasoning model.

Confirm the cause

max_completion_tokens replaced max_tokens for newer models, and the rename is semantic: reasoning models generate internal reasoning tokens that are billed but never returned, so "tokens generated" and "tokens you see back" are no longer the same number. The new parameter works on all current models, making it the portable choice.

The trap: the budget covers ALL output tokens including hidden reasoning. A small budget can be eaten entirely by internal thinking, leaving visible content empty with finish_reason: "length". An empty answer with finish_reason length on a reasoning model usually means the budget starved, not that the model had nothing to say.

The fix

1. Send max_completion_tokens everywhere, never max_tokens. One code path covers GPT-4o, GPT-3.5-era, and reasoning models.
2. Size it generously for reasoning models. Empty content plus finishreason length means raise the budget substantially or lower `reasoningeffort` to cap thinking overhead.
3. Grep every call site when migrating, including wrappers and SDK defaults. The ones you miss 400 at 2am.

Verify the fix

Call the reasoning model with the new parameter and confirm 200. Deliberately test the edge: a tiny budget should produce the empty-content plus finish_reason length signature, and your code should read that as "budget too small", not "model broken".

When to use this

• This covers exactly what the title says: OpenAI 400 Unsupported parameter max_tokens.
• You are setting this up for the first time, or auditing an existing setup.
• You want the key gotchas in one place before you start.

When not to use this

• You are doing a different workflow with OpenAI; these steps are specific to the title above.
• You need the full reference docs; this is the short path, not the manual.

Compatibility

• Mentions 3.5 in the original; behavior may differ on much older or newer releases.

Reasoning models return 400 Unsupported parameter for maxtokens with the instruction to use maxcompletiontokens, which works across current models and budgets all output tokens including hidden reasoning tokens. The reasoning guide shows reasoningtokens reported under usage outputtokensdetails: billed output that never appears in the response (https://platform.openai.com/docs/guides/error-codes, https://platform.openai.com/docs/guides/reasoning).