community-help
Need some emergency support here... top 10 ranking site all api requests being blocked
errors
limit
Saved chats not visible when I sign-in to another device
Image size/dimensions in Image Gen?
User not found Error
Got charged twice when adding credits
errors
For a platform that is basically a single massive api ... The api documentation is seriously Lacking
models optimized for RAG
Unable to add "Nebius (Fast)" to "ignored providers" in settings
errors
How to find list of supported parameters for each individual provider?
Cannot add credits
OpenRouter Rankings
HTTP 429 google/gemini-2.0-flash-exp:free is temporarily rate-limited upstream
Can´t refill credits.
Question about the BYOK
No “reasoning” parameter in Presets?
I´ve made a Payment And had no Credits!!!
I made the payment but it is not reflected in my credit
New Provider Onboarding
grok-fast-code1 model
Regarding the refund
Inquiry Regarding Cost Charges Based on Response Results
Why is the cost of these two requests 10 times different? I think there is something wrong with the
Automatically charge problem
which models support logit_bias
Being charged for free Model
Step3 rejects multimodal requests
Trouble with buying credits
Empty Tool Call Response when Streaming from gpt-oss-120b Provided by BaseTen
Provider error for nextbit
errors
Empty response body in some request
BYOK Google Vertex
new rate limit is awful
Integrations (BYOK)
stealth model 404
Negative credits even though haven't spent nearly as much.
BYOK Amazon bedrock not working with Anthropic models
I got a very large request to gemini-pro-1.5 that I do not recognize
Inquiry Regarding Unexpected Charges While Using a Free Model
Inquiry Regarding Compliance with OpenRouter Terms of Service
how-to
Credits not showing up.
Unable to buy credits
how-to
Credit No Reflection
Charged for use of a free endpoint?
Credits Transactions Not Going Through (Stripe)
errors
CREDITS NOT REFLECTED YET
Repeated 429 for google/gemini-2.0-flash-exp:free — cf-ray 97a6f9ab492e83bd-MAD
Free limit remaining yet it says limit reached
Kimi k2 made 4 calls for one message
Chat: cannot specify thinking tokens anymore?