feat(providers): refresh model catalogs and support custom routing (#7851)

* feat(providers): refresh model catalogs and support custom routing

* fix(providers): add verified Qwen 3.8 release dates

Author: waleedlatif1

apps/docs/content/docs/workflows/blocks/agent.mdx

@@ -27,6 +27,10 @@ Answer in two sentences, cite the doc you used, and never guess a price.
 
 The model that runs the step. Defaults to `claude-sonnet-4-6`. Type or pick any model from OpenAI, Anthropic, Google, xAI, Groq, Cerebras, DeepSeek, Azure, AWS Bedrock, Google Vertex, or OpenRouter, or a local model through Ollama or VLLM.
 
+For a custom cloud deployment, enter its provider prefix and model ID: `azure/my-deployment`, `azure-anthropic/my-deployment`, `bedrock/my-inference-profile`, or `vertex/my-gemini-model`. The prefix selects the provider and shows its credential fields even when the ID is absent from the catalog. Bedrock accepts full inference profile ARNs after `bedrock/`; Vertex uses the Gemini API and accepts Google model resource names. The deployment must support the selected provider's API. Custom IDs have no catalog pricing or token limits.
+
+Ollama Cloud, OpenRouter, Fireworks, Together AI, Baseten, Ollama, vLLM, and LiteLLM load their available models from the configured provider. New models appear through that discovery without a Sim catalog release. You can also enter a namespaced ID directly, such as `ollama-cloud/deepseek-v4.1-flash`, `openrouter/provider/model`, or `ollama/my-local-model`. Provider prefixes are case-insensitive; the model ID after the prefix keeps its original casing.
+
 ### Files
 
 Files for the model to read: images for a vision-capable model, or documents for text. Upload them on the block, or pass a file from an earlier block, such as an upload trigger or an [API](/workflows/blocks/api) response, with a connection tag.
@@ -110,18 +114,19 @@ Live tool-call chips stream for **OpenAI, Anthropic, Azure Anthropic, Google, Ve
 
 | Provider | Streamed thinking | Models |
 |----------|-------------------|--------|
-| OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `gpt-6-astra`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-pro`, `gpt-5.5`, `gpt-5.4-pro`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.2-pro`, `gpt-5.2`, `gpt-5.1`, `gpt-5-pro`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `o4-mini`, `o3`, `o3-mini`, `o1` |
+| OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `gpt-6-astra`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-pro`, `gpt-5.5`, `gpt-5.4-pro`, `gpt-5.4`, `gpt-5.4-mini`, `gpt-5.4-nano`, `gpt-5.3-codex`, `gpt-5.2-pro`, `gpt-5.2`, `gpt-5.1`, `gpt-5-pro`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `o4-mini`, `o3`, `o3-mini`, `o1` |
 | Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `claude-fable-5-1`, `claude-fable-5`, `claude-sonnet-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-sonnet-4-6`, `claude-opus-4-5`, `claude-sonnet-4-5`, `claude-haiku-4-5` |
-| Azure OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `azure/gpt-5.4`, `azure/gpt-5.4-mini`, `azure/gpt-5.4-nano`, `azure/gpt-5.2`, `azure/gpt-5.1`, `azure/gpt-5.1-codex`, `azure/gpt-5`, `azure/gpt-5-mini`, `azure/gpt-5-nano`, `azure/o3`, `azure/o4-mini` |
-| Azure Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `azure-anthropic/claude-opus-4-6`, `azure-anthropic/claude-opus-4-5`, `azure-anthropic/claude-sonnet-4-5`, `azure-anthropic/claude-opus-4-1`, `azure-anthropic/claude-haiku-4-5` |
-| Google | Summaries only | `gemini-3.8-flash`, `gemini-3.6-flash`, `gemini-3.5-flash-lite`, `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite` |
-| Vertex AI | Summaries only | `vertex/gemini-3.5-flash`, `vertex/gemini-3.1-pro-preview`, `vertex/gemini-3.1-flash-lite`, `vertex/gemini-3-flash-preview`, `vertex/gemini-2.5-pro`, `vertex/gemini-2.5-flash`, `vertex/gemini-2.5-flash-lite` |
-| DeepSeek | Full thinking deltas | `deepseek-v4-pro`, `deepseek-v4-flash`, `deepseek-reasoner` |
+| Azure OpenAI | Summaries only — Requires OpenAI organization verification; falls back to no summaries. | `azure/gpt-6-astra`, `azure/gpt-5.6-sol`, `azure/gpt-5.6-terra`, `azure/gpt-5.6-luna`, `azure/gpt-5.5`, `azure/gpt-5.4-pro`, `azure/gpt-5.4`, `azure/gpt-5.4-mini`, `azure/gpt-5.4-nano`, `azure/gpt-5.2`, `azure/gpt-5.1`, `azure/gpt-5.1-codex`, `azure/gpt-5`, `azure/gpt-5-mini`, `azure/gpt-5-nano`, `azure/o3`, `azure/o4-mini` |
+| Azure Anthropic | Summaries only — These generations omit full thinking; Sim requests summarized thinking on streaming runs. | `azure-anthropic/claude-fable-5-1`, `azure-anthropic/claude-opus-5`, `azure-anthropic/claude-opus-4-8`, `azure-anthropic/claude-opus-4-7`, `azure-anthropic/claude-opus-4-6`, `azure-anthropic/claude-opus-4-5`, `azure-anthropic/claude-sonnet-5`, `azure-anthropic/claude-sonnet-4-6`, `azure-anthropic/claude-sonnet-4-5`, `azure-anthropic/claude-opus-4-1`, `azure-anthropic/claude-haiku-4-5` |
+| Google | Summaries only | `gemini-3.8-flash`, `gemini-3.7-flash`, `gemini-3.6-flash`, `gemini-3.5-flash-lite`, `gemini-3.5-flash`, `gemini-3.1-pro-preview`, `gemini-3.1-flash-lite`, `gemini-3-flash-preview`, `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-2.5-flash-lite` |
+| Vertex AI | Summaries only | `vertex/gemini-3.8-flash`, `vertex/gemini-3.7-flash`, `vertex/gemini-3.6-flash`, `vertex/gemini-3.5-flash-lite`, `vertex/gemini-3.5-flash`, `vertex/gemini-3.1-pro-preview`, `vertex/gemini-3.1-flash-lite`, `vertex/gemini-3-flash-preview`, `vertex/gemini-2.5-pro`, `vertex/gemini-2.5-flash`, `vertex/gemini-2.5-flash-lite` |
+| DeepSeek | Full thinking deltas | `deepseek-v4-pro`, `deepseek-flash`, `deepseek-v4-flash`, `deepseek-reasoner` |
 | xAI | Full thinking deltas | `grok-4.6`, `grok-4.5`, `grok-4.3`, `grok-4.20-multi-agent-0309` |
-| Groq | Full thinking deltas | `groq/openai/gpt-oss-120b`, `groq/openai/gpt-oss-20b`, `groq/openai/gpt-oss-safeguard-20b`, `groq/qwen/qwen3.6-27b` |
+| Cerebras | Full thinking deltas | `cerebras/qwen-3.8-27b` |
+| Groq | Full thinking deltas | `groq/openai/gpt-oss-120b`, `groq/openai/gpt-oss-20b`, `groq/openai/gpt-oss-safeguard-20b`, `groq/qwen/qwen3.8-27b`, `groq/qwen/qwen3.6-27b` |
 | Meta | Not streamed | `muse-spark-1.3`, `muse-spark-1.1` |
-| Kimi | Full thinking deltas | `kimi-k2.6` |
-| Z.ai | Full thinking deltas | `glm-5.3`, `glm-5.2`, `glm-5.1`, `glm-5`, `glm-5-turbo`, `glm-4.7`, `glm-4.6`, `glm-4.5`, `glm-4.5-air` |
+| Kimi | Full thinking deltas | `kimi-k3`, `kimi-k2.6` |
+| Z.ai | Full thinking deltas | `glm-5.3`, `glm-5.3-flash`, `glm-5.2`, `glm-5.1`, `glm-5`, `glm-5-turbo`, `glm-4.7`, `glm-4.6`, `glm-4.5`, `glm-4.5-air` |
 
 {/* agent-stream-capabilities:end */}
 

apps/sim/app/api/providers/ollama-cloud/models/route.test.ts

@@ -144,6 +144,29 @@ describe('GET /api/providers/ollama-cloud/models', () => {
     expect(fetchAuthHeader()).toBe('Bearer byok-ollama-key')
   })
 
+  it('discovers newly available models on subsequent requests without a static catalog update', async () => {
+    grantWorkspaceAccess()
+    mockGetBYOKKey.mockResolvedValue({ apiKey: 'byok-ollama-key' })
+    mockFetch
+      .mockResolvedValueOnce(okResponse({ models: [{ name: 'kimi-k3' }] }))
+      .mockResolvedValueOnce(
+        okResponse({
+          models: [{ name: 'kimi-k3' }, { name: 'deepseek-v4.1-flash' }, { name: 'glm-5.3' }],
+        })
+      )
+
+    const first = await GET(requestWithWorkspace('ws-1'))
+    expect(await first.json()).toEqual({ models: ['ollama-cloud/kimi-k3'] })
+    const refreshed = await GET(requestWithWorkspace('ws-1'))
+    expect(await refreshed.json()).toEqual({
+      models: ['ollama-cloud/kimi-k3', 'ollama-cloud/deepseek-v4.1-flash', 'ollama-cloud/glm-5.3'],
+    })
+    expect(mockFetch).toHaveBeenLastCalledWith(
+      OLLAMA_CLOUD_TAGS_URL,
+      expect.objectContaining({ cache: 'no-store' })
+    )
+  })
+
   it('does not call getBYOKKey when there is a workspaceId but no session', async () => {
     mockGetSession.mockResolvedValue(null)
 

apps/sim/blocks/provider-credentials.test.ts

@@ -0,0 +1,34 @@
+/**
+ * @vitest-environment node
+ */
+import { describe, expect, it } from 'vitest'
+import { evaluateSubBlockCondition } from '@/lib/workflows/subblocks/visibility'
+import { getProviderCredentialSubBlocks } from '@/blocks/utils'
+
+describe('provider credential visibility', () => {
+  const subBlocks = getProviderCredentialSubBlocks().filter(({ id }) => id !== 'apiKey')
+
+  it.each([
+    ['azure/MyDeployment', ['azureEndpoint', 'azureApiVersion']],
+    ['AZURE/MyDeployment', ['azureEndpoint', 'azureApiVersion']],
+    ['azure-anthropic/MyDeployment', ['azureEndpoint', 'azureApiVersion']],
+    ['bedrock/custom-profile', ['bedrockAccessKeyId', 'bedrockSecretKey', 'bedrockRegion']],
+    [
+      'vertex/publishers/google/models/custom-gemini',
+      ['vertexCredential', 'vertexManualCredential', 'vertexProject', 'vertexLocation'],
+    ],
+    [
+      'VERTEX/CustomModel',
+      ['vertexCredential', 'vertexManualCredential', 'vertexProject', 'vertexLocation'],
+    ],
+    ['gpt-4o', []],
+    ['unknown/model', []],
+    ['', []],
+  ])('shows only the routed provider credentials for %s', (model, expected) => {
+    const visible = subBlocks
+      .filter((subBlock) => evaluateSubBlockCondition(subBlock.condition, { model }))
+      .map(({ id }) => id)
+
+    expect(visible).toEqual(expected)
+  })
+})

apps/sim/blocks/utils.test.ts

@@ -31,7 +31,8 @@ const { mockProviders } = vi.hoisted(() => ({
   },
 }))
 
-vi.mock('@/providers/models', () => ({
+vi.mock('@/providers/models', async (importOriginal) => ({
+  ...(await importOriginal<typeof import('@/providers/models')>()),
   getProviderFileAttachment: vi
     .fn()
     .mockReturnValue({ maxBytes: 10 * 1024 * 1024, strategy: 'inline' }),
@@ -180,6 +181,16 @@ describe('getApiKeyCondition / shouldRequireApiKeyForModel', () => {
   })
 
   describe('provider store lookup (client-side)', () => {
+    it('requires the cloud key even when a local discovered name uses its namespace', () => {
+      mockProviders.value.ollama.models = ['azure/MyDeployment', 'ollama-cloud/MyModel']
+      expect(evaluateCondition('azure/MyDeployment')).toBe(true)
+      expect(evaluateCondition('ollama-cloud/MyModel')).toBe(true)
+    })
+
+    it('does not require an API key for an undiscovered namespaced Ollama model', () => {
+      expect(evaluateCondition('OLLAMA/Org/CustomModel')).toBe(false)
+    })
+
     it('does not require API key when model is in the Ollama store bucket', () => {
       mockProviders.value.ollama.models = ['llama3:latest', 'mistral:latest']
       expect(evaluateCondition('llama3:latest')).toBe(false)

apps/sim/blocks/utils.ts

@@ -6,12 +6,14 @@ import { getScopesForService } from '@/lib/oauth/utils'
 import { containsReference } from '@/lib/workflows/sanitization/references'
 import type { SubBlockConfig } from '@/blocks/types'
 import {
+  findProviderFromModel,
   getBaseModelProviders,
   getHostedModels,
   getModelSunsetStatus,
   getProviderIcon,
   getProviderModels,
   isAutoModel,
+  isCustomModelId,
   orderModelIdsByReleaseDate,
   SIM_AUTO_MODEL_ID,
 } from '@/providers/models'
@@ -20,8 +22,6 @@ import type { ProviderId } from '@/providers/types'
 import { getProviderFromModel } from '@/providers/utils'
 import { useProvidersStore } from '@/stores/providers/store'
 
-export const VERTEX_MODELS = getProviderModels('vertex')
-export const BEDROCK_MODELS = getProviderModels('bedrock')
 export const AZURE_MODELS = [
   ...getProviderModels('azure-openai'),
   ...getProviderModels('azure-anthropic'),
@@ -164,10 +164,16 @@ function shouldRequireApiKeyForModel(model: string): boolean {
   ) {
     return false
   }
-  if (normalizedModel.startsWith('vllm/') || normalizedModel.startsWith('litellm/')) {
+  if (
+    normalizedModel.startsWith('ollama/') ||
+    normalizedModel.startsWith('vllm/') ||
+    normalizedModel.startsWith('litellm/')
+  ) {
     return false
   }
 
+  if (isCustomModelId(normalizedModel)) return true
+
   const storeProvider = getProviderFromStore(normalizedModel)
   if (storeProvider === 'ollama' || storeProvider === 'vllm' || storeProvider === 'litellm')
     return false
@@ -272,6 +278,14 @@ export function getCohereRerankerApiKeyCondition() {
   }
 }
 
+function getModelProviderCondition(...providerIds: ProviderId[]) {
+  return (values?: Record<string, unknown>) => {
+    const model = typeof values?.model === 'string' ? values.model : ''
+    const provider = findProviderFromModel(model.trim())
+    return buildModelVisibilityCondition(model, provider !== null && providerIds.includes(provider))
+  }
+}
+
 /**
  * Returns the standard provider credential subblocks used by LLM-based blocks.
  * This includes: Vertex AI OAuth, API Key, Azure (OpenAI + Anthropic), Vertex AI config, and Bedrock config.
@@ -290,10 +304,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       requiredScopes: getScopesForService('vertex-ai'),
       placeholder: 'Select Google Cloud account',
       required: true,
-      condition: {
-        field: 'model',
-        value: VERTEX_MODELS,
-      },
+      condition: getModelProviderCondition('vertex'),
     },
     {
       id: 'vertexManualCredential',
@@ -303,10 +314,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       mode: 'advanced',
       placeholder: 'Enter credential ID',
       required: true,
-      condition: {
-        field: 'model',
-        value: VERTEX_MODELS,
-      },
+      condition: getModelProviderCondition('vertex'),
     },
     {
       id: 'apiKey',
@@ -326,10 +334,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       placeholder: 'https://your-resource.services.ai.azure.com',
       connectionDroppable: false,
       hideWhenEnvSet: 'NEXT_PUBLIC_AZURE_CONFIGURED',
-      condition: {
-        field: 'model',
-        value: AZURE_MODELS,
-      },
+      condition: getModelProviderCondition('azure-openai', 'azure-anthropic'),
     },
     {
       id: 'azureApiVersion',
@@ -338,10 +343,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       placeholder: 'Enter API version',
       connectionDroppable: false,
       hideWhenEnvSet: 'NEXT_PUBLIC_AZURE_CONFIGURED',
-      condition: {
-        field: 'model',
-        value: AZURE_MODELS,
-      },
+      condition: getModelProviderCondition('azure-openai', 'azure-anthropic'),
     },
     {
       id: 'vertexProject',
@@ -351,10 +353,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       placeholder: 'your-gcp-project-id',
       connectionDroppable: false,
       required: true,
-      condition: {
-        field: 'model',
-        value: VERTEX_MODELS,
-      },
+      condition: getModelProviderCondition('vertex'),
     },
     {
       id: 'vertexLocation',
@@ -363,10 +362,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       placeholder: 'us-central1',
       connectionDroppable: false,
       required: true,
-      condition: {
-        field: 'model',
-        value: VERTEX_MODELS,
-      },
+      condition: getModelProviderCondition('vertex'),
     },
     {
       id: 'bedrockAccessKeyId',
@@ -377,10 +373,7 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       connectionDroppable: false,
       required: true,
       hideWhenEnvSet: 'NEXT_PUBLIC_BEDROCK_DEFAULT_CREDENTIALS',
-      condition: {
-        field: 'model',
-        value: BEDROCK_MODELS,
-      },
+      condition: getModelProviderCondition('bedrock'),
     },
     {
       id: 'bedrockSecretKey',
@@ -391,21 +384,15 @@ export function getProviderCredentialSubBlocks(): SubBlockConfig[] {
       connectionDroppable: false,
       required: true,
       hideWhenEnvSet: 'NEXT_PUBLIC_BEDROCK_DEFAULT_CREDENTIALS',
-      condition: {
-        field: 'model',
-        value: BEDROCK_MODELS,
-      },
+      condition: getModelProviderCondition('bedrock'),
     },
     {
       id: 'bedrockRegion',
       title: 'AWS Region',
       type: 'short-input',
       placeholder: 'us-east-1',
       connectionDroppable: false,
-      condition: {
-        field: 'model',
-        value: BEDROCK_MODELS,
-      },
+      condition: getModelProviderCondition('bedrock'),
     },
   ]
 }

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

@@ -451,6 +451,99 @@ describe('getBYOKKey', () => {
   })
 })
 
+describe('getApiKeyWithBYOK provider classification', () => {
+  const dynamicProviders = [
+    'ollama',
+    'vllm',
+    'litellm',
+    'fireworks',
+    'together',
+    'baseten',
+    'ollama-cloud',
+  ] as const
+
+  beforeEach(() => {
+    vi.clearAllMocks()
+    resetDbChainMock()
+    mockIsHosted.value = true
+    mockEnv.AZURE_OPENAI_API_KEY = 'azure-env-key'
+    mockEnv.AZURE_ANTHROPIC_API_KEY = 'azure-anthropic-env-key'
+    mockEnv.VLLM_API_KEY = 'vllm-env-key'
+    mockEnv.LITELLM_API_KEY = 'litellm-env-key'
+    dbChainMockFns.orderBy.mockResolvedValue([storedKey('other-provider-key')])
+    mockDecryptSecret.mockImplementation(async (encrypted: string) => ({
+      decrypted: encrypted.replace('encrypted-', 'decrypted-'),
+    }))
+  })
+
+  it.each(dynamicProviders)(
+    'keeps Azure credentials when %s discovery contains the same model ID',
+    async (discoveredProvider) => {
+      const model = 'AZURE/CustomDeployment'
+      vi.mocked(useProvidersStore.getState).mockReturnValue({
+        providers: Object.fromEntries(
+          dynamicProviders.map((provider) => [
+            provider,
+            { models: provider === discoveredProvider ? [model] : [] },
+          ])
+        ),
+      } as ReturnType<typeof useProvidersStore.getState>)
+
+      const result = await getApiKeyWithBYOK('azure-openai', model, uniqueWorkspaceId())
+
+      expect(result).toEqual({ apiKey: 'azure-env-key', isBYOK: false })
+      expect(dbChainMockFns.where).not.toHaveBeenCalled()
+      expect(mockGetRotatingApiKey).not.toHaveBeenCalled()
+    }
+  )
+
+  it.each([
+    ['vertex', 'vertex/CustomDeployment', 'vertex-access-token'],
+    ['azure-anthropic', 'azure-anthropic/CustomDeployment', 'azure-anthropic-user-key'],
+  ])(
+    'retains caller credentials for %s despite a local model name collision',
+    async (provider, model, apiKey) => {
+      vi.mocked(useProvidersStore.getState).mockReturnValue({
+        providers: Object.fromEntries(dynamicProviders.map((name) => [name, { models: [model] }])),
+      } as ReturnType<typeof useProvidersStore.getState>)
+
+      expect(await getApiKeyWithBYOK(provider, model, uniqueWorkspaceId(), apiKey)).toEqual({
+        apiKey,
+        isBYOK: false,
+      })
+      expect(dbChainMockFns.where).not.toHaveBeenCalled()
+    }
+  )
+
+  it.each([
+    ['ollama', 'empty'],
+    ['vllm', 'vllm-env-key'],
+    ['litellm', 'litellm-env-key'],
+  ])('preserves %s authentication for a custom unprefixed model', async (provider, apiKey) => {
+    expect(await getApiKeyWithBYOK(provider, 'MyCustomModel', uniqueWorkspaceId())).toEqual({
+      apiKey,
+      isBYOK: false,
+    })
+    expect(dbChainMockFns.where).not.toHaveBeenCalled()
+  })
+
+  it.each(['vllm', 'litellm'])(
+    'prefers a caller key to the configured %s key for a local model',
+    async (provider) => {
+      expect(
+        await getApiKeyWithBYOK(provider, 'MyCustomModel', uniqueWorkspaceId(), 'caller-key')
+      ).toEqual({ apiKey: 'caller-key', isBYOK: false })
+    }
+  )
+
+  it('uses Bedrock credentials for an uncataloged inference profile', async () => {
+    expect(
+      await getApiKeyWithBYOK('bedrock', 'BEDROCK/MyInferenceProfile', uniqueWorkspaceId())
+    ).toEqual({ apiKey: 'placeholder', isBYOK: false })
+    expect(dbChainMockFns.where).not.toHaveBeenCalled()
+  })
+})
+
 describe('getApiKeyWithBYOK for Fireworks', () => {
   const HOSTED_POOL_MODEL = 'fireworks/glm-5.2'