diff --git a/.github/workflows/pullfrog.yml b/.github/workflows/pullfrog.yml
index 6516ae2e..d5030252 100644
--- a/.github/workflows/pullfrog.yml
+++ b/.github/workflows/pullfrog.yml
@@ -34,22 +34,21 @@ jobs:
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
           CLAUDE_CODE_OAUTH_TOKEN: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          GOOGLE_GENERATIVE_AI_API_KEY:
-            ${{ secrets.GOOGLE_GENERATIVE_AI_API_KEY }}
+          GOOGLE_GENERATIVE_AI_API_KEY: ${{ secrets.GOOGLE_GENERATIVE_AI_API_KEY }}
           GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
           XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
           DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
           MOONSHOT_API_KEY: ${{ secrets.MOONSHOT_API_KEY }}
           OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
           OPENCODE_API_KEY: ${{ secrets.OPENCODE_API_KEY }}
-          
+
           # for Amazon Bedrock (https://docs.pullfrog.com/bedrock)
           # AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.AWS_BEARER_TOKEN_BEDROCK }}
           # AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           # AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           # AWS_REGION: us-east-1
           # BEDROCK_MODEL_ID: <bedrock-model-id>
-          
+
           # for Google Vertex AI (https://docs.pullfrog.com/vertex)
           # VERTEX_SERVICE_ACCOUNT_JSON: ${{ secrets.VERTEX_SERVICE_ACCOUNT_JSON }}
           # GOOGLE_CLOUD_PROJECT: my-project
diff --git a/lua/CopilotChat/client.lua b/lua/CopilotChat/client.lua
index 7bbc65d8..5a9898f3 100644
--- a/lua/CopilotChat/client.lua
+++ b/lua/CopilotChat/client.lua
@@ -323,10 +323,11 @@ function Client:ask(opts)
     local headers = self:authenticate(provider_name)
     local resolved_model = provider.resolve_model(headers, opts.model)
     opts.model = resolved_model
-    model_config = models[opts.model]
-    if not model_config then
-      error('Resolved model not found: ' .. opts.model)
-    end
+    -- The resolved model may not be present in the models cache when
+    -- model_picker_enabled is false for all API models (e.g. restricted accounts).
+    -- Fall back to the original config (e.g. from the 'auto' entry) so the
+    -- request can still be sent with the correct model id.
+    model_config = models[opts.model] or model_config
   end
 
   local options = {
diff --git a/lua/CopilotChat/config/providers.lua b/lua/CopilotChat/config/providers.lua
index ea5eea71..7ba89657 100644
--- a/lua/CopilotChat/config/providers.lua
+++ b/lua/CopilotChat/config/providers.lua
@@ -635,11 +635,18 @@ M.copilot = {
       error(err)
     end
 
+    -- Get all chat models, preferring those with model_picker_enabled.
+    -- Fall back to all chat models if none are picker-enabled (e.g. restricted accounts).
+    local all_chat_data = vim.tbl_filter(function(model)
+      return model.capabilities and model.capabilities.type == 'chat'
+    end, response.body.data)
+
+    local picker_enabled_data = vim.tbl_filter(function(model)
+      return model.model_picker_enabled
+    end, all_chat_data)
+
     local models = vim
-      .iter(response.body.data)
-      :filter(function(model)
-        return model.capabilities.type == 'chat' and model.model_picker_enabled
-      end)
+      .iter(#picker_enabled_data > 0 and picker_enabled_data or all_chat_data)
       :map(function(model)
         local supported_endpoints = model.supported_endpoints or {}
         -- Pre-compute whether this model uses the Responses API