community-help

OpenRouter doesn't use the AWS bedrock integration I configured and still uses credits 7 messages

Mar 25, 2025, 3:02 PM

3.7 Sonet - EMPTY result from chat.completion with gen-124... that returns 404 when i query it 5 messages

Mar 25, 2025, 2:39 PM errors

claude-3-7-sonnet error occurred during call 12 messages

Mar 25, 2025, 2:39 PM

How to switch off or "ignore" specific model providers 22 messages

Mar 25, 2025, 1:28 PM

Chats on mobile open router page do not appear when logged into another device on desktop 3 messages

Mar 25, 2025, 1:24 PM

What to type on console command 4 messages

Mar 25, 2025, 10:01 AM how-to

output token limit is capping at 100 3 messages

Mar 25, 2025, 9:13 AM errors how-to

Error on `response_format` does not support streaming 6 messages

Mar 25, 2025, 9:13 AM

Gemini Prompt caching? 2 messages

Mar 25, 2025, 8:44 AM

Can't see Account Settings under Organization 11 messages

Mar 25, 2025, 12:51 AM

Specifying reasoning params 10 messages

Mar 24, 2025, 11:04 PM

Rate Limits / SAAS 86 messages

Mar 24, 2025, 10:49 PM

Unable to access the paid models after upgrade 30 messages

Mar 24, 2025, 9:17 PM errors

Gemini is not working 8 messages

Mar 24, 2025, 6:44 PM

Unable to delete my Provisioning Key 6 messages

Mar 24, 2025, 5:30 PM

Reasoning model bug - empty token sending back with langchain 6 messages

Mar 24, 2025, 4:14 PM

I can't login. Keep getting "failed security validations" 3 messages

Mar 24, 2025, 4:10 PM

OpenRouter Locations 3 messages

Mar 24, 2025, 9:02 AM

Does Openrouter API supports multiple concurrent requests? 3 messages

Mar 24, 2025, 8:52 AM

Deepseek R1 in JSON mode (Fireworks provider) Is no longer working correctly, after Fireworks update 9 messages

Mar 23, 2025, 7:38 PM errors

Mistral Small 3.1 24B (free) support tools, but non-free does not 4 messages

Mar 23, 2025, 8:45 AM errors

Huge lump sum charged with no trace 8 messages

Mar 22, 2025, 1:56 PM

I am using gemini's “gemini-2.0-flash-exp” model, and the gemini api supports the following paramete 2 messages

Mar 22, 2025, 3:16 AM how-to

Why. WebP images are getting blurred? 2 messages

Mar 22, 2025, 2:12 AM

o1-pro: "More credits are required to run this request" 4 messages

Mar 21, 2025, 5:08 PM

Perplexity Streaming Output 2 messages

Mar 21, 2025, 4:53 PM

Fraudulent charges 3 messages

Mar 21, 2025, 2:59 PM

Cors issue 4 messages

Mar 21, 2025, 2:21 PM errors

Rate Limits & Requests Extension for Free models 10 messages

Mar 21, 2025, 1:40 PM

Rate limits 6 messages

Mar 21, 2025, 11:19 AM

can't load https://openrouter.ai/ in firefox 5 messages

Mar 21, 2025, 9:41 AM

Why do my API keys always expire? 2 messages

Mar 21, 2025, 8:49 AM

PowerAutomate says THE MODEL 'API/V1' IS NOT AVAILABLE 3 messages

Mar 21, 2025, 8:41 AM

Provide model search as api 7 messages

Mar 21, 2025, 8:06 AM

Selecting a Specific Provider Without Quantization 3 messages

Mar 20, 2025, 3:22 PM how-to

DeepSeek r1 discounted costs 2 messages

Mar 20, 2025, 2:43 PM

Inference prices for Gemma-3-27b-it are much higher than advertised 2 messages

Mar 20, 2025, 2:13 PM

Massive increase in token usage 24 messages

Mar 20, 2025, 12:35 PM

Usage export? 10 messages

Mar 20, 2025, 12:07 PM

authorize doesn't work 5 messages

Mar 20, 2025, 2:29 AM how-to

Why? Why is the model selected different from the one provided? 10 messages

Mar 20, 2025, 2:17 AM

Bug report regarding MetaMask 6 messages

Mar 19, 2025, 6:17 PM errors

Persisting chat and prevent amount of tokens 4 messages

Mar 19, 2025, 5:18 PM

gemini 2.0 flash thinking rate limit 6 messages

Mar 19, 2025, 8:41 AM

We want to use your service 6 messages

Mar 18, 2025, 8:36 PM

broken on firefox 26 messages

Mar 18, 2025, 4:21 PM

Seeking an Alternative to GPT-4o-mini: Evaluating DeepSeek via OpenRouter 7 messages

Mar 18, 2025, 4:07 PM

alipay payment method? 9 messages

Mar 18, 2025, 1:52 PM

Paypal Option 2 messages

Mar 18, 2025, 12:23 PM

Filter inappropriate prompts 6 messages

Mar 18, 2025, 10:59 AM