[AIG]Chat-completions-endpoint

src/content/docs/ai-gateway/chat-completion.mdx

@@ -0,0 +1,110 @@
+---
+title: OpenAI Compatibility
+pcx_content_type: configuration
+sidebar:
+  order: 4
+---
+
+Cloudflare's AI Gateway offers an OpenAI-compatible `/chat/completions` endpoint, enabling integration with multiple AI providers using a single URL. This feature simplifies the integration process, allowing for seamless switching between different models without significant code modifications.
+
+## Endpoint URL
+
+```txt
+https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat/chat/completions
+```
+
+Replace `{account_id}` and `{gateway_id}` with your Cloudflare account and gateway IDs.
+
+## Parameters
+
+Switch providers by changing the `model` and `apiKey` parameters.
+
+Specify the model using `{provider}/{model}` format. For example:
+
+- `openai/gpt-4o-mini`
+- `google-ai-studio/gemini-2.0-flash`
+- `anthropic/claude-3-haiku`
+
+## Examples
+
+### OpenAI SDK
+
+```js
+import OpenAI from "openai";
+const client = new OpenAI({
+	apiKey: "YOUR_PROVIDER_API_KEY", // Provider API key
+	baseURL:
+		"https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat/chat/completions",
+});
+
+const response = await client.chat.completions.create({
+	model: "google-ai-studio/gemini-2.0-flash",
+	messages: [{ role: "user", content: "What is Cloudflare?" }],
+});
+
+console.log(response.choices[0].message.content);
+```
+
+### cURL
+
+```bash
+curl -X POST https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat/chat/completions \
+  --header 'Authorization: Bearer {openai_token}' \
+  --header 'Content-Type: application/json' \
+  --data '{
+    "model": "google-ai-studio/gemini-2.0-flash",
+    "messages": [
+      {
+        "role": "user",
+        "content": "What is Cloudflare?"
+      }
+    ]
+  }'
+```
+
+### Universal provider
+
+You can also use this pattern with a [Universal Endpoint](/ai-gateway/universal/).
+
+```ts title="index.ts"
+export interface Env {
+	AI: Ai;
+}
+
+export default {
+	async fetch(request: Request, env: Env) {
+		return env.AI.gateway("default").run({
+			provider: "compat",
+			endpoint: "chat/completions",
+			headers: {
+				authorization: "Bearer ",
+			},
+			query: {
+				model: "google-ai-studio/gemini-2.0-flash",
+				messages: [
+					{
+						role: "user",
+						content: "What is Cloudflare?",
+					},
+				],
+			},
+		});
+	},
+};
+```
+
+## Supported Providers
+
+The OpenAI-compatible endpoint supports models from the following providers:
+
+- [Anthropic](/ai-gateway/providers/anthropic/)
+- [OpenAI](/ai-gateway/providers/openai/)
+- [Groq](/ai-gateway/providers/groq/)
+- [Mistral](/ai-gateway/providers/mistral/)
+- [Cohere](/ai-gateway/providers/cohere/)
+- [Perplexity](/ai-gateway/providers/perplexity/)
+- [Workers AI](/ai-gateway/providers/workersai/)
+- [Google-AI-Studio](/ai-gateway/providers/google-ai-studio/)
+- [Grok](/ai-gateway/providers/grok/)
+- [DeepSeek](/ai-gateway/providers/deepseek/)
+- [Cerebras](/ai-gateway/providers/cerebras/)

src/content/docs/ai-gateway/configuration/index.mdx

@@ -4,7 +4,7 @@ title: Configuration
 sidebar:
   group:
     hideIndex: true
-  order: 4
+  order: 5
 ---
 
 import { DirectoryListing } from "~/components";

src/content/docs/ai-gateway/providers/anthropic.mdx

@@ -3,6 +3,8 @@ title: Anthropic
 pcx_content_type: get-started
 ---
 
+import { Render } from "~/components";
+
 [Anthropic](https://www.anthropic.com/) helps build reliable, interpretable, and steerable AI systems.
 
 ## Endpoint
@@ -65,3 +67,17 @@ const message = await anthropic.messages.create({
 	max_tokens: maxTokens,
 });
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Anthropic",
+		jsonexample: `
+{
+	"model": "anthropic/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/cerebras.mdx

@@ -6,6 +6,8 @@ sidebar:
     text: Beta
 ---
 
+import { Render } from "~/components";
+
 [Cerebras](https://inference-docs.cerebras.ai/) offers developers a low-latency solution for AI model inference.
 
 ## Endpoint
@@ -41,3 +43,17 @@ curl https://gateway.ai.cloudflare.com/v1/ACCOUNT_TAG/GATEWAY/cerebras/chat/comp
     ]
 }'
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Cerebras",
+		jsonexample: `
+{
+	"model": "cerebras/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/cohere.mdx

@@ -3,6 +3,8 @@ title: Cohere
 pcx_content_type: get-started
 ---
 
+import { Render } from "~/components";
+
 [Cohere](https://cohere.com/) build AI models designed to solve real-world business challenges.
 
 ## Endpoint
@@ -72,3 +74,17 @@ chat = co.chat(
 print(chat)
 
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Cohere",
+		jsonexample: `
+{
+	"model": "cohere/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/deepseek.mdx

@@ -6,6 +6,8 @@ sidebar:
     text: Beta
 ---
 
+import { Render } from "~/components";
+
 [DeepSeek](https://www.deepseek.com/) helps you build quickly with DeepSeek's advanced AI models.
 
 ## Endpoint
@@ -80,3 +82,17 @@ try {
 	return new Response(e);
 }
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "DeepSeek",
+		jsonexample: `
+{
+	"model": "deepseek/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/google-ai-studio.mdx

@@ -3,6 +3,8 @@ title: Google AI Studio
 pcx_content_type: get-started
 ---
 
+import { Render } from "~/components";
+
 [Google AI Studio](https://ai.google.dev/aistudio) helps you build quickly with Google Gemini models.
 
 ## Endpoint
@@ -69,3 +71,17 @@ const model = genAI.getGenerativeModel(
 
 await model.generateContent(["What is Cloudflare?"]);
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Google AI Studio",
+		jsonexample: `
+{
+	"model": "google-ai-studio/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/grok.mdx

@@ -3,7 +3,9 @@ title: Grok
 pcx_content_type: get-started
 ---
 
-[Grok](https://docs.x.ai/docs#getting-started) is a general purpose model that can be used for a variety of tasks, including generating and understanding text, code, and function calling.
+import { Render } from "~/components";
+
+[Grok](https://docs.x.ai/docs#getting-started) is s a general purpose model that can be used for a variety of tasks, including generating and understanding text, code, and function calling.
 
 ## Endpoint
 
@@ -156,3 +158,17 @@ message = client.messages.create(
 
 print(message.content)
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Grok",
+		jsonexample: `
+{
+	"model": "grok/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/groq.mdx

@@ -3,6 +3,8 @@ title: Groq
 pcx_content_type: get-started
 ---
 
+import { Render } from "~/components";
+
 [Groq](https://groq.com/) delivers high-speed processing and low-latency performance.
 
 ## Endpoint
@@ -68,3 +70,17 @@ const chatCompletion = await groq.chat.completions.create({
 	model,
 });
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Groq",
+		jsonexample: `
+{
+	"model": "groq/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/index.mdx

@@ -4,7 +4,7 @@ title: Model providers
 sidebar:
   group:
     hideIndex: true
-  order: 3
+  order: 4
 ---
 
 Here is a quick list of the providers we support:

src/content/docs/ai-gateway/providers/mistral.mdx

@@ -3,6 +3,8 @@ title: Mistral AI
 pcx_content_type: get-started
 ---
 
+import { Render } from "~/components";
+
 [Mistral AI](https://mistral.ai) helps you build quickly with Mistral's advanced AI models.
 
 ## Endpoint
@@ -69,3 +71,17 @@ await client.chat.create({
 	],
 });
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Mistral",
+		jsonexample: `
+{
+	"model": "mistral/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/perplexity.mdx

@@ -3,6 +3,8 @@ title: Perplexity
 pcx_content_type: get-started
 ---
 
+import { Render } from "~/components";
+
 [Perplexity](https://www.perplexity.ai/) is an AI powered answer engine.
 
 ## Endpoint
@@ -67,3 +69,17 @@ const chatCompletion = await perplexity.chat.completions.create({
 	max_tokens: maxTokens,
 });
 ```
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Perplexity",
+		jsonexample: `
+{
+	"model": "perplexity/{model}"
+}`
+
+    }}
+
+/>

src/content/docs/ai-gateway/providers/workersai.mdx

@@ -117,3 +117,17 @@ Workers AI supports the following parameters for AI gateways:
   - Controls whether the request should [skip the cache](/ai-gateway/configuration/caching/#skip-cache-cf-aig-skip-cache).
 - `cacheTtl` number
   - Controls the [Cache TTL](/ai-gateway/configuration/caching/#cache-ttl-cf-aig-cache-ttl).
+
+<Render
+	file="chat-completions-providers"
+	product="ai-gateway"
+	params={{
+		name: "Workers AI",
+		jsonexample: `
+{
+	"model": "workers-ai/{model}"
+}`
+
+    }}
+
+/>