Model error diagnosis

OpenAI: GPT-5.1-Codex-Max | model rate limited

OpenAI: GPT-5.1-Codex-Max returning 429 / model rate limited means you should first confirm whether model ID openai/gpt-5.1-codex-max is visible for this OpenAI key, then separate permission, context, capability, rate limit, or route issues.

Model

openai/gpt-5.1-codex-max

OpenAI: GPT-5.1-Codex-Max

Provider

OpenAI

62 models in catalog

Error type

model rate limited

rate-limited

Status code

429

global model route

Model error summary

Model

openai/gpt-5.1-codex-max

Error type

rate-limited

Status code

429

Read-only check. Detection data burns after 5 minutes.

What this model error usually means

OpenAI: GPT-5.1-Codex-Max returning 429 / model rate limited means you should first confirm whether model ID openai/gpt-5.1-codex-max is visible for this OpenAI key, then separate permission, context, capability, rate limit, or route issues.

Model: openai/gpt-5.1-codex-max
Provider: OpenAI
Status code: 429

How to prove it during checking

Read-only check. Detection data burns after 5 minutes.

List models: confirm whether openai/gpt-5.1-codex-max is actually visible instead of guessing from the display name.
Light probe: use minimal input to verify whether OpenAI returns the same 429, then record the error body.
Compare model facts: context 400,000, input $1.25, output $10.
supports include_reasoning
supports max_completion_tokens
supports max_tokens
supports reasoning

Next action

OpenAI: GPT-5.1-Codex-Max model rate limited should not end at failed. Return the next move: change model ID, add permission, reduce context, disable unsupported capability, change route, monitor, or hold listing.

Context: 400,000
Price: $1.25 / $10
Read-only check. Detection data burns after 5 minutes.

Open key checker

Read-only check. Detection data burns after 5 minutes.

Open models

OpenAI: GPT-5.1-Codex-Max

Open providers

OpenAI