Docs update for PR #2 on helicone-test

docs/features/experiments.mdx

@@ -9,12 +9,12 @@ import QuestionsSection from "/snippets/questions-section.mdx";
 
 <Info>
   **Who can use this feature**: Anyone on Pro or Enterprise
-  [plan](https://www.helicone.ai/pricing), this feature will be charged at cost.
+  [plan](https://www.helicone.ai/pricing), this feature will be charged at cost. Experiments supports multiple LLM providers, including OpenAI, Google, Mistralai, X-AI, and Meta-Llama, enabling a broader range of AI capabilities.
 </Info>
 
 ## What are Experiments?
 
-Helicone's Experiments is designed to help you tune your LLM prompt, test it on production data, and verify your iterations with quantifiable data. In Helicone, you can define and run LLM-as-a-judge or custom evaluators, then compare the results between prompts side-by-side to determine the best one for production.
+Helicone's Experiments is designed to help you tune your LLM prompt, test it on production data, and verify your iterations with quantifiable data. This feature also supports a wide range of LLM providers, including Google, Mistralai, X-AI, and Meta-Llama. In Helicone, you can define and run LLM-as-a-judge or custom evaluators, then compare the results between prompts side-by-side to determine the best one for production.
 
 <Frame>
   <img
@@ -28,6 +28,7 @@ Helicone's Experiments is designed to help you tune your LLM prompt, test it on
 - **Prevent regression:** Prompt engineering is iterative. Engineers want to prevent regression with each prompt change.
 - **Model update:** LLMs are sensitive to prompt changes. As new models with advanced capability come out, prompts that worked previously can become less effective.
 - **Quick feedback loop:** Instead of waiting for user feedback, get feedback immediately and adjust before pushing to production.
+- **Model variety:** The experiment feature supports a wide range of models from multiple providers, including Google, Mistralai, X-AI, and Meta-Llama. This ensures coverage of a wide range of AI capabilities and more robust prompt optimization.
 
 ## What is the prompt iteration workflow?
 
@@ -41,7 +42,7 @@ Helicone's Experiments is designed to help you tune your LLM prompt, test it on
 
 ### 1. Create a new experiment
 
-Head to the `Experiment` tab. If you have a prompt with Helicone, click on `start from a prompt`, then choose the desired prompt version. Otherwise, click on `start from scratch`.
+Head to the `Experiment` tab. If you have a prompt with Helicone, click on `start from a prompt`, then choose the desired prompt version (including new models from Google, Mistralai, X-AI, and Meta-Llama). Otherwise, click on `start from scratch`.
 
 <Frame>
   <img

docs/getting-started/integration-method/custom.mdx

@@ -1,7 +1,7 @@
 ---
 title: "Custom Model Integration"
 sidebarTitle: "Custom Model"
-description: "Integrate any custom LLM, including open-source models like Llama and GPT-Neo, with Helicone. Step-by-step guide for both NodeJS and Curl implementations to connect your proprietary or open-source models."
+description: "Integrate any custom LLM, including open-source or third-party models like Llama, GPT-Neo, Google PaLM, Mistralai, X-AI, or Meta-Llama, with Helicone. Step-by-step guide for both NodeJS and Curl implementations to connect your proprietary or open-source models."
 "twitter:title": "Custom Model Integration - Helicone OSS LLM Observability"
 ---
 

docs/getting-started/integration-method/hyperbolic.mdx

@@ -7,7 +7,7 @@ icon: "cloud"
 iconType: "solid"
 ---
 
-You can seamlessly integrate Helicone with the OpenAI compatible models that are deployed on Hyperbolic.
+You can seamlessly integrate Helicone with the OpenAI compatible models that are deployed on Hyperbolic. In addition to the example below using a Meta-Llama model, you can also specify other open-source LLMs from Google, Mistralai, or X-AI.
 
 The integration process closely mirrors the [proxy approach](/integrations/openai/javascript). The only distinction lies in the modification of the base_url to point to the dedicated Hyperbolic endpoint `https://hyperbolic.helicone.ai/v1`.
 

docs/getting-started/integration-method/openllmetry.mdx

@@ -141,6 +141,9 @@ response = client.chat.completions.create(
 - [x] Cohere
 - [x] Bedrock
 - [x] Google AI Platform
+- [x] Mistralai
+- [x] X-AI
+- [x] Meta-Llama
 
 # Other Integrations
 

docs/getting-started/integration-method/vercelai.mdx

@@ -1,7 +1,7 @@
 ---
 title: "Vercel AI SDK Integration"
 sidebarTitle: "Vercel AI"
-description: "Use Vercel AI SDK to integrate with Helicone to log your OpenAI usage."
+description: "Use Vercel AI SDK to integrate with Helicone to log your LLM usage (OpenAI, Anthropic, Google, Mistralai, X-AI, Meta-Llama, etc.)."
 "twitter:title": "Vercel AI SDK Integration - Helicone OSS LLM Observability"
 icon: "triangle"
 iconType: "solid"

docs/guides/cookbooks/debugging.mdx

@@ -18,7 +18,7 @@ We are currently developing dedicated error filters to further enhance your debu
 
 # Debugging Prompts with Playground
 
-<Info>Currently, only ChatGPT is supported</Info>
+<Info>The Playground supports multiple LLM providers, including ChatGPT, Google, Mistralai, X-AI, and Meta-Llama.</Info>
 
 Helicone's 'Playground' feature offers a platform for debugging your 'prompt'. This tool enables you to test your prompt and swiftly observe the model's output for minor adjustments within the Helicone environment. Here's a step-by-step guide on how to use it:
 

docs/guides/cookbooks/experiments.mdx

@@ -43,7 +43,7 @@ To start an experiment, first, go to the [Prompts](https://www.helicone.ai/promp
 </Frame>
   </Step>
   <Step title="Configure your experiment">
-    Select the dataset, model and provider keys.
+    Select the dataset, model and provider keys. Helicone now supports a wide range of providers, including Google, Mistralai, X-AI, and Meta-Llama.
     <Tip>
       To run your experiment on a random dataset, click `Generate random
       dataset`. We will pick up to 10 random data from your existing

docs/introduction.mdx

@@ -39,9 +39,9 @@ The optimal method to integrate with Helicone is through our Gateway.
 
   </Card>
    <Card title="OpenRouter" href="/getting-started/integration-method/openrouter">
-
-  </Card>
-     <Card title="LiteLLM" href="/getting-started/integration-method/litellm">
+    Supports new providers from Google, Mistralai, X-AI, and Meta-Llama
+   </Card>
+      <Card title="LiteLLM" href="/getting-started/integration-method/litellm">
   </Card>
 </CardGroup>
 

docs/quick-start.mdx

@@ -12,7 +12,7 @@ iconType: "solid"
 
 <CardGroup cols={4}>
   <Card
-    title="OpenAI"
+    title="OpenAI, Google, Mistralai, X-AI, and Meta-Llama"
     href="/getting-started/providers/openai"
     icon={
       <svg