feat(providers): add OrcaRouter as a named provider

autoqa/checklist.md

@@ -98,6 +98,7 @@ In Remote Model Providers:
 	- [ ] Anthropic
 	- [ ] Cohere
 	- [ ] OpenRouter
+	- [ ] OrcaRouter
 	- [ ] Mistral
 	- [ ] Groq
 	- [ ] Gemini

docs/src/pages/docs/desktop/remote-models/_meta.json

@@ -20,6 +20,9 @@
   "openrouter": {
     "title": "OpenRouter"
   },
+  "orcarouter": {
+    "title": "OrcaRouter"
+  },
   "huggingface": {
     "title": "Hugging Face"
   }

docs/src/pages/docs/desktop/remote-models/orcarouter.mdx

@@ -0,0 +1,101 @@
+---
+title: OrcaRouter
+description: A step-by-step guide on integrating Atomic Chat with OrcaRouter.
+keywords:
+  [
+    Jan,
+    Customizable Intelligence, LLM,
+    local AI,
+    privacy focus,
+    free and open source,
+    private and offline,
+    conversational AI,
+    no-subscription fee,
+    large language models,
+    OrcaRouter integration,
+    OrcaRouter,
+  ]
+---
+
+import { Callout, Steps } from 'nextra/components'
+import { Settings, Plus } from 'lucide-react'
+
+# OrcaRouter
+
+## Integrate OrcaRouter with Atomic Chat
+
+[OrcaRouter](https://www.orcarouter.ai) is an AI gateway that routes every
+request to the best model for the job — mixing frontier models, open-weight
+models, and long-context specialists behind one unified, OpenAI-compatible
+API. It also runs gateway-level, zero-trust security for AI agents on the same
+endpoint — screening every prompt/response and governing every tool call on a
+default-deny basis, with no application code changes.
+
+Atomic Chat supports the OrcaRouter API, so you can use one key to reach any
+of the 150+ models OrcaRouter routes to (Anthropic, Google, DeepSeek, MiniMax
+and more) without juggling a separate API key per provider.
+
+## Integrate OrcaRouter with Atomic Chat
+
+<Steps>
+
+### Step 1: Get Your API Key
+1. Visit [OrcaRouter](https://www.orcarouter.ai) and sign in
+2. Create & copy a new API key (keys are prefixed `sk-orca-`) or copy your existing one
+
+<Callout type='info'>
+`orcarouter/auto` is OrcaRouter's smart routing model: send every request to
+it and the gateway picks the cheapest model that satisfies the request, so
+you get frontier quality without the frontier price.
+</Callout>
+
+### Step 2: Configure Atomic Chat
+
+1. Navigate to the **Settings** page (<Settings width={16} height={16} style={{display:"inline"}}/>)
+2. Under **Model Providers**, select **OrcaRouter**
+3. Insert your **API Key**
+
+### Step 3: Start Using OrcaRouter Models
+
+1. Pick any existing **Chat** or create a new one
+2. Select any model from **model selector** under OrcaRouter
+3. Start chatting
+
+</Steps>
+
+## Available Models Through OrcaRouter
+
+Atomic Chat automatically lists OrcaRouter's available models via its
+`/v1/models` endpoint. For custom configurations:
+
+**Model Field Settings:**
+- Leave empty to use your account's default model
+- Specify a model using the format: `orcarouter/<router-name>` or
+  `<provider>/<model-name>`
+- The full model catalog is available at [https://www.orcarouter.ai/models](https://www.orcarouter.ai/models)
+
+**Examples of Model IDs:**
+- Smart router: `orcarouter/auto`
+- Claude via OrcaRouter: `anthropic/claude-sonnet-4.6`
+- Gemini via OrcaRouter: `google/gemini-3-flash-preview`
+
+## Troubleshooting
+
+Common issues and solutions:
+
+**1. API Key Issues**
+- Verify your API key is correct and starts with `sk-orca-`
+- Check you have sufficient credits in your OrcaRouter account
+- Ensure you have access to the model you're trying to use
+
+**2. Connection Problems**
+- Check your internet connection
+- Verify the API base URL is `https://api.orcarouter.ai/v1`
+- Look for error messages in [Atomic Chat's logs](/docs/desktop/troubleshooting#how-to-get-error-logs)
+
+**3. Model Unavailable**
+- Confirm the model is currently available on OrcaRouter
+- Check if you're using the correct model ID format (`orcarouter/` prefix for routers)
+- Verify the provider is currently operational
+
+Need more help? Join our [Discord community](https://discord.com/invite/8wGSsvmg4V) or check the [OrcaRouter documentation](https://docs.orcarouter.ai).

tests/checklist.md

@@ -113,6 +113,7 @@ In Remote Model Providers:
     - [ ] [0.7.0] Azure
 	- [ ] Cohere
 	- [ ] OpenRouter
+	- [ ] OrcaRouter
 	- [ ] Mistral
 	- [ ] Groq
 	- [ ] Gemini

web-app/src/constants/models.ts

@@ -777,6 +777,15 @@ export const providerModels = {
     supportsToolCalls: true,
     supportsN: true,
   },
+  'orcarouter': {
+    models: true,
+    supportsCompletion: true,
+    supportsStreaming: true,
+    supportsJSON: true,
+    supportsImages: true,
+    supportsToolCalls: true,
+    supportsN: true,
+  },
   'nvidia': {
     models: ['moonshotai/kimi-k2.5', 'minimaxai/minimax-m2.5', 'z-ai/glm5'],
     supportsCompletion: true,

web-app/src/lib/__tests__/models.test.ts

@@ -418,6 +418,13 @@ describe('getModelCapabilities', () => {
     expect(capabilities).not.toContain(ModelCapabilities.VISION)
   })
 
+  it('handles orcarouter like other OpenAI-compatible providers', () => {
+    const capabilities = getModelCapabilities('orcarouter', 'orcarouter/auto')
+    expect(capabilities).toEqual([ModelCapabilities.COMPLETION])
+    expect(capabilities).not.toContain(ModelCapabilities.TOOLS)
+    expect(capabilities).not.toContain(ModelCapabilities.VISION)
+  })
+
   it('handles model not in capability list', () => {
     const capabilities = getModelCapabilities('xai', 'grok-2-vision-1212')
     expect(capabilities).toContain(ModelCapabilities.COMPLETION)

web-app/src/lib/__tests__/utils.test.ts

@@ -23,6 +23,9 @@ describe('getProviderLogo', () => {
     expect(getProviderLogo('openai')).toBe('/images/model-provider/openai.svg')
     expect(getProviderLogo('gemini')).toBe('/images/model-provider/gemini.svg')
     expect(getProviderLogo('nvidia')).toBe('/images/model-provider/nvidia.svg')
+    expect(getProviderLogo('orcarouter')).toBe(
+      '/images/model-provider/orcarouter.svg'
+    )
   })
 
   it('returns undefined for unknown providers', () => {
@@ -36,6 +39,7 @@ describe('getProviderTitle', () => {
     expect(getProviderTitle('llamacpp')).toBe('llama.cpp turboquant')
     expect(getProviderTitle('openai')).toBe('OpenAI')
     expect(getProviderTitle('openrouter')).toBe('OpenRouter')
+    expect(getProviderTitle('orcarouter')).toBe('OrcaRouter')
     expect(getProviderTitle('gemini')).toBe('Gemini')
     expect(getProviderTitle('nvidia')).toBe('NVIDIA NIM')
   })

web-app/src/lib/model-factory.ts

@@ -767,6 +767,7 @@ export class ModelFactory {
       case 'moonshot':
       case 'minimax':
       case 'openrouter':
+      case 'orcarouter':
       case 'huggingface':
       case 'nvidia':
       case 'ollama':

web-app/src/lib/utils.ts

@@ -93,6 +93,8 @@ export function getProviderLogo(provider: string) {
       return '/images/model-provider/mistral.svg'
     case 'openrouter':
       return '/images/model-provider/open-router.svg'
+    case 'orcarouter':
+      return '/images/model-provider/orcarouter.svg'
     case 'groq':
       return '/images/model-provider/groq.svg'
     case 'cohere':
@@ -176,6 +178,8 @@ export const getProviderTitle = (provider: string) => {
       return 'OpenAI'
     case 'openrouter':
       return 'OpenRouter'
+    case 'orcarouter':
+      return 'OrcaRouter'
     case 'gemini':
       return 'Gemini'
     case 'huggingface':