feedback-and-requests
Cerebras gpt-oss-120b: Response format 'json_schema' with strict=True is not supported by this model
Request
Feedback
OpenRouter's Performance: Are the Claims Legit?
Feedback
Some model /endpoints return 500
Feedback
ChatGPT-5 is not available through OpenRouter API even without streaming
Feedback
High granularity average API output speed for popular models
Request
API Key Error: 405 Method Not Allowed on /v1/audio/speech
Request
No Venice thread
Feedback
Split Free Models used by 0 Credit users and Free Models used by Users with credits Please
Request
I am once again asking for embedding model/endpoint support
Request
Model Spend Date Filtering
Request
Rate limits
Request
What is the difference between openai/gpt-5-chat and openai/gpt-5?
Request
Feedback
Verbosity parameter for GPT-5
Request
Are there plans to add HRM model from Sapient?
Request
Blocked by Azure/OpenAI
Feedback
FP4 models are unacceptable especially for coding models. There’s no way to filter this as a paying
Feedback
Lack of compatibility with Windows 8.1
Request
Feedback
Some models throwing a 404
Feedback
Question: Undocumented 45 RPM Rate Limit for Claude Opus
Feedback
Is Starcannon still available?
Feedback
Adding OVHcloud Provider
Request
Add support for w&b (weights and biases) inference (cheap)
Request
Feedback
Ability to use new Amazon Bedrock API Keys for inference
Request
Feedback
Unsloth models on OpenRouter
Request
Setting response_format to json_schema is working unless I also set provider order for QWEN models.
Feedback
Implement url context for gemini models
Request
Bug: Impossible to specify deepinfra/turbo as provider
Feedback
The Chutes Limit
Feedback
Chatroom update is a disaster
Feedback
Calling Kimi K2 with tool use enabled from AutoGen, I get a lot of malformed tool use requests
Request
Feedback
Allow OpenRouter to be connected to self-hosted LLM engines like vLLM, Ollama, etc.
Request
CrofAI
Request
Add UI Tars 1.5 7b (its on Parasail)
Request
Chat function not working in Firefox
Feedback
Paypal payment option
Request
Feedback
Bugs with new Chat web UI update
Feedback
Bug on perplexity/sonar-deep-research?
Feedback
Normalize tool calls from Novita
Request
Feedback
Text Completion broken on OR's side
Feedback
Request to enable GPT-3.5 Turbo 16K on my OpenRouter account
Request
Claude Sonnet 4 selected, but Claude Sonnet 3.5 used.
Request
Feedback
yo is the grok4 chat on the website broken for anyone else?
Feedback
Baidu-Ernie gets ignored when specified as first model in model array
Request
Feedback
RogueRose103B User Request
Request
New focused discussion / building with openrouter channel
Feedback
vertex-ai global location with BYOK integration
Request
i forget key
Request
deepseek/deepseek-v3-pro model request
Request
Export All Chats Option
Request
我的服务器部署在中国成都。为什么请求deepseek0528 API的时候， 回复相应很慢 足足5到6秒了。 我也冲了钱了。还是很慢啊。 服务商那里看到写的 0.36s 的相应. 我也试过在AWs上
Request
Feedback