#Cerebras Upstream is Always Rate Limited

1 messages · Page 1 of 1 (latest)

nova saffron
#
error: {
  message: 'Provider returned error',
  code: 429,
  metadata: {
    raw: 'qwen/qwen3-235b-a22b-thinking-2507 is temporarily rate-limited upstream. Please retry shortly, or add your own key to accumulate your rate limits: https://openrouter.ai/settings/integrations',
    provider_name: 'Cerebras'
  }
}
worldly egretBOT
#

I'm an AI assistant - my answers may be incorrect and I cannot see screenshots. Please verify information with the OpenRouter docs.

The error you are seeing indicates an upstream rate limit from the provider "Cerebras" for the model qwen/qwen3-235b-a22b-thinking-2507. The error message specifically says:

"qwen/qwen3-235b-a22b-thinking-2507 is temporarily rate-limited upstream. Please retry shortly, or add your own key to accumulate your rate limits: https://openrouter.ai/settings/integrations"

Here’s what you can do:

  1. Retry after some time — This type of rate limit is usually temporary.
  2. Add your own key — Linking your own API key for the upstream provider may help bypass the shared pool’s rate limits. You can do this at OpenRouter Integrations.
  3. Provider Routing — If your request allows routing to alternate providers, OpenRouter may try to recover by routing to a healthy provider when upstream errors occur. See details about provider routing here.

If the issue persists, please check with the mods on Discord for further help.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.

OpenRouter

A router for LLMs and other AI models

OpenRouter

A router for LLMs and other AI models

OpenRouter

A router for LLMs and other AI models

nova saffron
#

Is this because the openrouter account on cerebras is rate limited, or all accounts on cerebras are rate limited? If it's the former, it's no use to add byok.

worldly egretBOT
#

I don't have specific documentation for whether rate limits on Cerebras apply only to the OpenRouter shared account or to all accounts (including BYOK). Please verify with the mods or check the OpenRouter docs directly for the most accurate information.

For reference, the Qwen3-235B-A22B-Thinking-2507 model routes requests to multiple providers, including Cerebras, and supports adding your own API key to "accumulate your rate limits" Qwen3 235B A22B Providers. However, the documentation does not clarify if BYOK bypasses upstream-wide rate limits.

For real-time or account-specific rate limit details, contacting the mods in Discord is recommended.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.

OpenRouter

A router for LLMs and other AI models