Cloudflare Developers

CD

Cloudflare Developers

Welcome to the official Cloudflare Developers server. Here you can ask for help and stay updated with the latest news

Join

Do you know why I cannot create new

Do you know why I cannot create new gateway? I can create it with my dev account, but cannot create it with pr account. any ideas pls?

Hi, guys! I'm trying to use Ai Gateway

Hi, guys! I'm trying to use Ai Gateway to cache requests for Gemini using Google Ai Studio but maybe i am doing something wrong :/ I am getting some errors regarding the system_instruction and generationConfig parameters The same request works by using the direct endpoint on google https://generativelanguage.googleapis.com/v1beta/models/...

that's exactly right, but actually just

that's exactly right, but actually just trying it again, I can't replicate this. I've tried a bunch of different things and FINALLY narrowed it down. The problem is in the messages array, when passing an array to content instead of a string, it doesn't work. Here's my code as an example:...

Azure costs analisis

Question regarding cost for azure open ai

May I ask if there is a gateway amount

May I ask if there is a gateway amount limit for each account? thank you

When using AI Gateway with Vertex AI (

When using AI Gateway with Vertex AI (Gemini 1.5 Pro), it seems like streaming is broken. It buffers everything.

Hey, trying to understand

Hey, trying to understand - you're using multiple azure openai models, so that's likely setting a different cache key each time - you'd like to get the same response each time though, because it's the same prompt, even though it's using different models is that correct?...

I'm using Perplexity AI with the

I'm using Perplexity AI with the universal endpoint on AI Gateway. I have already set up groq and workers AI with the universal endpoint. However, when sending a request to perplexity through the universal endpoint, I am getting this error:
At body: Input should be a dictionary or an instance of ApiChatCompletionsRequest
At body: Input should be a dictionary or an instance of ApiChatCompletionsRequest
...

Anthropic on universal Gateway

``` import requests import json def test_anthropic_api():...

Groq support & cases for Custom base URL

Any plans to support Groq? https://console.groq.com/docs/openai Groq's API is implemented the same as the OpenAI API spec, so I would think it'd be relatively straightforward to add them as a provider I want to use them as their cost per million tokens is very competitive, but I'll need a fallback provider (OpenAI or something else) if they fail, which is where I'm hoping AI gateway can come in 🙏...

What headers come back?

I have one question. If I use Azure and I move to ai gateway will I still be able to receive the headers from Azure? I tend to use simple fecth and since it's a fetch I was wondering if the original headers are also provided. Thank you.

any chance we'll see something like this

any chance we'll see something like this for the models cloudflare uses?

Also on the roadmap is the possibility

Also on the roadmap is the possibility to create Gateways via API, so that should also help for your use case, no?

Trying to use replicate via Ai Gateway

Trying to use replicate via Ai Gateway with universal endpoint, but can't get it work. Sending the example payload ``` { "version": "5fe0a3d7ac2852264a25279d1dfb798acbc4d49711d126646594e212cb821749",...

I'm also interested in having the AI

I'm also interested in having the AI gateway store API keys and protect that with cloudflare zero trust. I'm currently doing that with a worker but I'm curious if there are plans to support secrets management natively