Issue #1 – 403 Forbidden Error

[vast obsidian]

When calling the endpoint https://openrouter.ai/api/v1/chat/completions, I initially received the following response:

403 Client Error: Forbidden for url: https://openrouter.ai/api/v1/chat/completions

I verified that my API key was valid, and I included the proper headers (Authorization, HTTP-Referer, and X-Title). However, the request was still rejected with a 403 error.

[wide heron]

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

To help debug your 403 Forbidden error, I need some details to pinpoint the issue:

1. What is the exact error message or response body you receive (including any message text, not just the status code)?
2. Which exact model identifier are you using in your request (e.g., openai/gpt-4o, google/gemini-2.5-pro, etc.)?
3. Can you share the specific code snippet you’re using to make the API call (with any sensitive info/redacted as needed)?

These details are critical to diagnose 403 errors, as described: “403 Invalid code or code_verifier: Make sure your user is logged in to OpenRouter, and that code_verifier and code_challenge_method are correct.” OAuth PKCE | Secure Authentication.

Once you provide these, I can direct you to the right troubleshooting steps or escalate as needed.

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

[vast obsidian]

Shortly after the 403 error, I received a new message:

“Your resource has been temporarily blocked because we detected behavior that may violate our content policy. For more details on Azure OpenAI service content policy, please visit https://aka.ms/aoaicodeofconduct”

I only use the API for normal chatbot interactions and content generation, and there was no sensitive, restricted, or disallowed content involved. I suspect this may have been caused by routing through an Azure node or a false positive in the content filter.

[wide heron]

The message you received:
“Your resource has been temporarily blocked because we detected behavior that may violate our content policy. For more details on Azure OpenAI service content policy, please visit https://aka.ms/aoaicodeofconduct”
implies the block likely came from an upstream Azure provider's automated moderation layer.

OpenRouter does route requests to different providers (including Azure and OpenAI) to maximize reliability and uptime, and some providers may have stricter or different moderation triggers. As stated:
“OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime. … When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it.”
GPT-4o (2024-08-06) - API, Providers, Stats

For moderation/false positive issues tied to Azure’s content policy, OpenRouter itself cannot directly remove these blocks—you must wait for the temporary block to expire, or adjust your prompt and request to avoid triggering the filter.

If you continue to experience blocks while NOT sending any restricted content, please email [e-mail] with full details so the team can investigate further. Azure moderation logic is proprietary and may sometimes yield false positives.

Learn more about request routing and provider error handling:
Provider Routing Docs

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