feat(litellm): add LiteLLM as AI gateway provider

apps/sim/.env.example

@@ -48,6 +48,8 @@ API_ENCRYPTION_KEY=your_api_encryption_key # Use `openssl rand -hex 32` to gener
 # OLLAMA_URL=http://localhost:11434  # URL for local Ollama server - uncomment if using local models
 # VLLM_BASE_URL=http://localhost:8000    # Base URL for your self-hosted vLLM (OpenAI-compatible)
 # VLLM_API_KEY=                          # Optional bearer token if your vLLM instance requires auth
+# LITELLM_BASE_URL=http://localhost:4000 # Base URL for your LiteLLM proxy (OpenAI-compatible)
+# LITELLM_API_KEY=                       # Optional bearer token if your LiteLLM proxy requires auth
 # FIREWORKS_API_KEY=                     # Optional Fireworks AI API key for model listing
 # NEXT_PUBLIC_BEDROCK_DEFAULT_CREDENTIALS=true  # Set when using AWS default credential chain (IAM roles, ECS task roles, IRSA). Hides credential fields in Agent block UI.
 # AZURE_OPENAI_ENDPOINT=                        # Azure OpenAI endpoint (hides field in UI when set alongside NEXT_PUBLIC_AZURE_CONFIGURED)

apps/sim/app/api/providers/litellm/models/route.ts

@@ -0,0 +1,70 @@
+import { createLogger } from '@sim/logger'
+import { getErrorMessage } from '@sim/utils/errors'
+import { type NextRequest, NextResponse } from 'next/server'
+import {
+  providerModelsResponseSchema,
+  vllmUpstreamResponseSchema,
+} from '@/lib/api/contracts/providers'
+import { env } from '@/lib/core/config/env'
+import { withRouteHandler } from '@/lib/core/utils/with-route-handler'
+import { filterBlacklistedModels, isProviderBlacklisted } from '@/providers/utils'
+
+const logger = createLogger('LiteLLMModelsAPI')
+
+export const GET = withRouteHandler(async (_request: NextRequest) => {
+  if (isProviderBlacklisted('litellm')) {
+    logger.info('LiteLLM provider is blacklisted, returning empty models')
+    return NextResponse.json({ models: [] })
+  }
+
+  const baseUrl = (env.LITELLM_BASE_URL || '').replace(/\/$/, '')
+
+  if (!baseUrl) {
+    logger.info('LITELLM_BASE_URL not configured')
+    return NextResponse.json({ models: [] })
+  }
+
+  try {
+    logger.info('Fetching LiteLLM models', { baseUrl })
+
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+    }
+
+    if (env.LITELLM_API_KEY) {
+      headers.Authorization = `Bearer ${env.LITELLM_API_KEY}`
+    }
+
+    const response = await fetch(`${baseUrl}/v1/models`, {
+      headers,
+      next: { revalidate: 60 },
+    })
+
+    if (!response.ok) {
+      logger.warn('LiteLLM service is not available', {
+        status: response.status,
+        statusText: response.statusText,
+      })
+      return NextResponse.json({ models: [] })
+    }
+
+    const data = vllmUpstreamResponseSchema.parse(await response.json())
+    const allModels = data.data.map((model) => `litellm/${model.id}`)
+    const models = filterBlacklistedModels(allModels)
+
+    logger.info('Successfully fetched LiteLLM models', {
+      count: models.length,
+      filtered: allModels.length - models.length,
+      models,
+    })
+
+    return NextResponse.json(providerModelsResponseSchema.parse({ models }))
+  } catch (error) {
+    logger.error('Failed to fetch LiteLLM models', {
+      error: getErrorMessage(error, 'Unknown error'),
+      baseUrl,
+    })
+
+    return NextResponse.json({ models: [] })
+  }
+})

apps/sim/app/workspace/[workspaceId]/providers/provider-models-loader.tsx

@@ -6,6 +6,7 @@ import { useParams } from 'next/navigation'
 import { useProviderModels } from '@/hooks/queries/providers'
 import {
   updateFireworksProviderModels,
+  updateLiteLLMProviderModels,
   updateOllamaProviderModels,
   updateOpenRouterProviderModels,
   updateVLLMProviderModels,
@@ -32,6 +33,8 @@ function useSyncProvider(provider: ProviderName, workspaceId?: string) {
         updateOllamaProviderModels(data.models)
       } else if (provider === 'vllm') {
         updateVLLMProviderModels(data.models)
+      } else if (provider === 'litellm') {
+        updateLiteLLMProviderModels(data.models)
       } else if (provider === 'openrouter') {
         void updateOpenRouterProviderModels(data.models)
         if (data.modelInfo) {
@@ -61,6 +64,7 @@ export function ProviderModelsLoader() {
   useSyncProvider('base')
   useSyncProvider('ollama')
   useSyncProvider('vllm')
+  useSyncProvider('litellm')
   useSyncProvider('openrouter')
   useSyncProvider('fireworks', workspaceId)
   return null

apps/sim/blocks/utils.test.ts

@@ -27,6 +27,7 @@ const { mockProviders } = vi.hoisted(() => ({
       base: { models: [] as string[], isLoading: false },
       ollama: { models: [] as string[], isLoading: false },
       vllm: { models: [] as string[], isLoading: false },
+      litellm: { models: [] as string[], isLoading: false },
       openrouter: { models: [] as string[], isLoading: false },
       fireworks: { models: [] as string[], isLoading: false },
     },
@@ -101,6 +102,7 @@ describe('getApiKeyCondition / shouldRequireApiKeyForModel', () => {
       base: { models: [], isLoading: false },
       ollama: { models: [], isLoading: false },
       vllm: { models: [], isLoading: false },
+      litellm: { models: [], isLoading: false },
       openrouter: { models: [], isLoading: false },
       fireworks: { models: [], isLoading: false },
     }
@@ -185,6 +187,11 @@ describe('getApiKeyCondition / shouldRequireApiKeyForModel', () => {
       expect(evaluateCondition('my-custom-model')).toBe(false)
     })
 
+    it('does not require API key when model is in the LiteLLM store bucket', () => {
+      mockProviders.value.litellm.models = ['litellm/anthropic/claude-sonnet-4-6']
+      expect(evaluateCondition('litellm/anthropic/claude-sonnet-4-6')).toBe(false)
+    })
+
     it('requires API key when model is in the fireworks store bucket', () => {
       mockProviders.value.fireworks.models = ['fireworks/llama-3']
       expect(evaluateCondition('fireworks/llama-3')).toBe(true)

apps/sim/blocks/utils.ts

@@ -51,13 +51,15 @@ export function getModelOptions() {
   const baseModels = providersState.providers.base.models
   const ollamaModels = providersState.providers.ollama.models
   const vllmModels = providersState.providers.vllm.models
+  const litellmModels = providersState.providers.litellm.models
   const openrouterModels = providersState.providers.openrouter.models
   const fireworksModels = providersState.providers.fireworks.models
   const allModels = Array.from(
     new Set([
       ...baseModels,
       ...ollamaModels,
       ...vllmModels,
+      ...litellmModels,
       ...openrouterModels,
       ...fireworksModels,
     ])
@@ -160,12 +162,13 @@ function shouldRequireApiKeyForModel(model: string): boolean {
   ) {
     return false
   }
-  if (normalizedModel.startsWith('vllm/')) {
+  if (normalizedModel.startsWith('vllm/') || normalizedModel.startsWith('litellm/')) {
     return false
   }
 
   const storeProvider = getProviderFromStore(normalizedModel)
-  if (storeProvider === 'ollama' || storeProvider === 'vllm') return false
+  if (storeProvider === 'ollama' || storeProvider === 'vllm' || storeProvider === 'litellm')
+    return false
   if (storeProvider) return true
 
   if (isOllamaConfigured) {

apps/sim/components/icons.tsx

@@ -4439,6 +4439,20 @@ export function VllmIcon(props: SVGProps<SVGSVGElement>) {
   )
 }
 
+export function LitellmIcon(props: SVGProps<SVGSVGElement>) {
+  return (
+    <svg {...props} fill='none' viewBox='0 0 72 72' xmlns='http://www.w3.org/2000/svg'>
+      <title>LiteLLM</title>
+      <image
+        href='data:image/png;base64,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'
+        width='72'
+        height='72'
+        preserveAspectRatio='xMidYMid meet'
+      />
+    </svg>
+  )
+}
+
 export function PosthogIcon(props: SVGProps<SVGSVGElement>) {
   return (
     <svg

apps/sim/hooks/queries/providers.ts

@@ -5,6 +5,7 @@ import { requestJson } from '@/lib/api/client/request'
 import {
   getBaseProviderModelsContract,
   getFireworksProviderModelsContract,
+  getLitellmProviderModelsContract,
   getOllamaProviderModelsContract,
   getOpenRouterProviderModelsContract,
   getVllmProviderModelsContract,
@@ -54,6 +55,8 @@ async function requestProviderModels(
       return requestJson(getOllamaProviderModelsContract, { signal })
     case 'vllm':
       return requestJson(getVllmProviderModelsContract, { signal })
+    case 'litellm':
+      return requestJson(getLitellmProviderModelsContract, { signal })
     case 'openrouter':
       return requestJson(getOpenRouterProviderModelsContract, { signal })
     case 'fireworks':

apps/sim/lib/api-key/byok.ts

@@ -74,6 +74,12 @@ export async function getApiKeyWithBYOK(
     return { apiKey: userProvidedKey || env.VLLM_API_KEY || 'empty', isBYOK: false }
   }
 
+  const isLitellmModel =
+    provider === 'litellm' || useProvidersStore.getState().providers.litellm.models.includes(model)
+  if (isLitellmModel) {
+    return { apiKey: userProvidedKey || env.LITELLM_API_KEY || 'empty', isBYOK: false }
+  }
+
   const isFireworksModel =
     provider === 'fireworks' ||
     useProvidersStore.getState().providers.fireworks.models.includes(model)

apps/sim/lib/api/contracts/providers.ts

@@ -207,6 +207,15 @@ export const getOpenRouterProviderModelsContract = defineRouteContract({
   },
 })
 
+export const getLitellmProviderModelsContract = defineRouteContract({
+  method: 'GET',
+  path: '/api/providers/litellm/models',
+  response: {
+    mode: 'json',
+    schema: providerModelsResponseSchema,
+  },
+})
+
 export const getFireworksProviderModelsContract = defineRouteContract({
   method: 'GET',
   path: '/api/providers/fireworks/models',

apps/sim/lib/copilot/tools/server/blocks/get-blocks-metadata-tool.ts

@@ -768,6 +768,7 @@ function callOptionsWithFallback(
       base: { models: staticModels.map((m) => m.id) },
       ollama: { models: [] },
       vllm: { models: [] },
+      litellm: { models: [] },
       openrouter: { models: [] },
       fireworks: { models: [] },
     },

apps/sim/lib/copilot/tools/server/workflow/edit-workflow/validation.ts

@@ -369,7 +369,7 @@ export function validateValueForSubBlockType(
               blockType,
               field: fieldName,
               value,
-              error: `Unknown model id "${trimmed}" for block "${blockType}". Read components/blocks/${blockType}.json (the model.options array) for valid ids; prefer entries with recommended: true and avoid deprecated: true. For user-configured models (Ollama, vLLM, OpenRouter, Fireworks), prefix the id with the provider slash, e.g. "ollama/llama3.1:8b".${suggestionText}`,
+              error: `Unknown model id "${trimmed}" for block "${blockType}". Read components/blocks/${blockType}.json (the model.options array) for valid ids; prefer entries with recommended: true and avoid deprecated: true. For user-configured models (Ollama, vLLM, LiteLLM, OpenRouter, Fireworks), prefix the id with the provider slash, e.g. "ollama/llama3.1:8b".${suggestionText}`,
             },
           }
         }

apps/sim/lib/core/config/env.ts

@@ -127,6 +127,8 @@ export const env = createEnv({
     OLLAMA_URL:                            z.string().url().optional(),            // Ollama local LLM server URL
     VLLM_BASE_URL:                         z.string().url().optional(),            // vLLM self-hosted base URL (OpenAI-compatible)
     VLLM_API_KEY:                          z.string().optional(),                  // Optional bearer token for vLLM
+    LITELLM_BASE_URL:                      z.string().url().optional(),            // LiteLLM proxy base URL (OpenAI-compatible)
+    LITELLM_API_KEY:                       z.string().optional(),                  // Optional bearer token for LiteLLM
     FIREWORKS_API_KEY:                     z.string().optional(),                  // Optional Fireworks AI API key for model listing
     COHERE_API_KEY:                        z.string().min(1).optional(),           // Cohere API key for reranker (rerank-v4.0-pro, rerank-v4.0-fast, rerank-v3.5)
     COHERE_API_KEY_1:                      z.string().min(1).optional(),           // Primary Cohere API key for rotation

apps/sim/providers/attachments.ts

@@ -24,6 +24,7 @@ export type AttachmentProvider =
   | 'fireworks'
   | 'ollama'
   | 'vllm'
+  | 'litellm'
   | 'xai'
   | 'deepseek'
   | 'cerebras'
@@ -93,6 +94,7 @@ const PROVIDER_SUPPORTED_LABELS: Record<AttachmentProvider, string> = {
   fireworks: 'images through image_url message parts on vision models',
   ollama: 'images through image_url message parts on vision models',
   vllm: 'images through image_url message parts on multimodal models',
+  litellm: 'images through image_url message parts on multimodal models',
   xai: 'images through image_url message parts on Grok vision models',
   deepseek: 'no file attachments in the current API adapter',
   cerebras: 'no file attachments in the current API adapter',
@@ -109,6 +111,7 @@ export function getAttachmentProvider(providerId: ProviderId | string): Attachme
   if (providerId === 'fireworks') return 'fireworks'
   if (providerId === 'ollama') return 'ollama'
   if (providerId === 'vllm') return 'vllm'
+  if (providerId === 'litellm') return 'litellm'
   if (providerId === 'xai') return 'xai'
   if (providerId === 'deepseek') return 'deepseek'
   if (providerId === 'cerebras') return 'cerebras'
@@ -247,6 +250,7 @@ function isMimeTypeSupportedByProvider(
     case 'fireworks':
     case 'ollama':
     case 'vllm':
+    case 'litellm':
     case 'xai':
       return isImageMimeType(mimeType)
     case 'deepseek':