🌉 feat: Integrate Helicone AI Gateway Provider (#10287)

* feat: integrate Helicone AI gateway provider

- Add Helicone provider support with automatic model fetching
- Implement custom API logic for Helicone model registry endpoint
- Enable access to 75+ models from multiple AI providers through Helicone gateway
- Add Helicone to supported providers list in README
- Include Helicone configuration in example YAML

* docs: add Helicone to supported providers list

* fix comments

* fixed backgroundless helicone icon asset

* removed unecessesary changes

* replace svg helicone image instead of png

README.md

@@ -56,7 +56,7 @@
   - [Custom Endpoints](https://www.librechat.ai/docs/quick_start/custom_endpoints): Use any OpenAI-compatible API with LibreChat, no proxy required
   - Compatible with [Local & Remote AI Providers](https://www.librechat.ai/docs/configuration/librechat_yaml/ai_endpoints):
     - Ollama, groq, Cohere, Mistral AI, Apple MLX, koboldcpp, together.ai,
-    - OpenRouter, Perplexity, ShuttleAI, Deepseek, Qwen, and more
+    - OpenRouter, Helicone, Perplexity, ShuttleAI, Deepseek, Qwen, and more
 
 - 🔧 **[Code Interpreter API](https://www.librechat.ai/docs/features/code_interpreter)**: 
   - Secure, Sandboxed Execution in Python, Node.js (JS/TS), Go, C/C++, Java, PHP, Rust, and Fortran

client/src/hooks/Endpoint/UnknownIcon.tsx

@@ -12,6 +12,7 @@ const knownEndpointAssets = {
   [KnownEndpoints.fireworks]: 'assets/fireworks.png',
   [KnownEndpoints.google]: 'assets/google.svg',
   [KnownEndpoints.groq]: 'assets/groq.png',
+  [KnownEndpoints.helicone]: 'assets/helicone.png',
   [KnownEndpoints.huggingface]: 'assets/huggingface.svg',
   [KnownEndpoints.mistral]: 'assets/mistral.png',
   [KnownEndpoints.mlx]: 'assets/mlx.png',

librechat.example.yaml

@@ -301,6 +301,22 @@ endpoints:
       dropParams: ['stop']
       modelDisplayLabel: 'OpenRouter'
 
+    # Helicone Example
+    - name: 'Helicone'
+      # For `apiKey` and `baseURL`, you can use environment variables that you define.
+      # recommended environment variables:
+      apiKey: '${HELICONE_KEY}'
+      baseURL: 'https://ai-gateway.helicone.ai'
+      headers:
+          x-librechat-body-parentmessageid: '{{LIBRECHAT_BODY_PARENTMESSAGEID}}'
+      models:
+        default: ['gpt-4o-mini', 'claude-4.5-sonnet', 'llama-3.1-8b-instruct', 'gemini-2.5-flash-lite']
+        fetch: true
+      titleConvo: true
+      titleModel: 'gpt-4o-mini'
+      modelDisplayLabel: 'Helicone'
+      iconURL: https://marketing-assets-helicone.s3.us-west-2.amazonaws.com/helicone.png
+
     # Portkey AI Example
     - name: 'Portkey'
       apiKey: 'dummy'
@@ -407,15 +423,12 @@ endpoints:
 #   # Jina Reranking Configuration
 #   jinaApiKey: '${JINA_API_KEY}'  # Your Jina API key
 #   jinaApiUrl: '${JINA_API_URL}'  # Custom Jina API URL (optional, defaults to https://api.jina.ai/v1/rerank)
-#   
 #   # Other rerankers
 #   cohereApiKey: '${COHERE_API_KEY}'
-#   
 #   # Search providers
 #   serperApiKey: '${SERPER_API_KEY}'
 #   searxngInstanceUrl: '${SEARXNG_INSTANCE_URL}'
 #   searxngApiKey: '${SEARXNG_API_KEY}'
-#   
 #   # Content scrapers
 #   firecrawlApiKey: '${FIRECRAWL_API_KEY}'
 #   firecrawlApiUrl: '${FIRECRAWL_API_URL}'

packages/data-provider/src/config.ts

@@ -911,6 +911,7 @@ export enum KnownEndpoints {
   fireworks = 'fireworks',
   deepseek = 'deepseek',
   groq = 'groq',
+  helicone = 'helicone',
   huggingface = 'huggingface',
   mistral = 'mistral',
   mlx = 'mlx',
@@ -926,6 +927,7 @@ export enum KnownEndpoints {
 
 export enum FetchTokenConfig {
   openrouter = KnownEndpoints.openrouter,
+  helicone = KnownEndpoints.helicone
 }
 
 export const defaultEndpoints: EModelEndpoint[] = [
@@ -958,6 +960,7 @@ export const alternateName = {
   [KnownEndpoints.deepseek]: 'DeepSeek',
   [KnownEndpoints.xai]: 'xAI',
   [KnownEndpoints.vercel]: 'Vercel',
+  [KnownEndpoints.helicone]: 'Helicone',
 };
 
 const sharedOpenAIModels = [