diff --git a/README.md b/README.md
index ccf2e60..7edc416 100644
--- a/README.md
+++ b/README.md
@@ -4,7 +4,7 @@ Groq Cloud runs LLM models fast and cheap. Llama 3, Mixtrel, Gemma, and more at
 
 [![speed-pricing](docs/images/groq-speed-price-20240421.png)](https://wow.groq.com/)
 
-Speed and pricing at 2024-04-21.
+Speed and pricing at 2024-04-21. Also see their [changelog](https://console.groq.com/docs/changelog) for new models and features.
 
 ## Groq Cloud API
 
@@ -185,7 +185,7 @@ Assistant reply with model gemma-7b-it:
 
 LLMs are increasingly supporting deferring to tools or functions to fetch data, perform calculations, or store structured data. Groq Cloud in turn then supports their tool implementations through its API.
 
-See the [Using Tools](https://console.groq.com/docs/tool-use) documentation for the list of models that currently support tools.
+See the [Using Tools](https://console.groq.com/docs/tool-use) documentation for the list of models that currently support tools. Others might support it sometimes and raise errors other times.
 
 ```ruby
 @client = Groq::Client.new(model_id: "mixtral-8x7b-32768")
diff --git a/lib/groq/client.rb b/lib/groq/client.rb
index 6d6ce8b..4c219bc 100644
--- a/lib/groq/client.rb
+++ b/lib/groq/client.rb
@@ -46,6 +46,13 @@ def chat(messages, model_id: nil, tools: nil)
     end
   end
 
+  def get(path:)
+    client.get do |req|
+      req.url path
+      req.headers["Authorization"] = "Bearer #{@api_key}"
+    end
+  end
+
   def post(path:, body:)
     client.post do |req|
       req.url path
diff --git a/lib/groq/model.rb b/lib/groq/model.rb
index b6a99e7..853ab55 100644
--- a/lib/groq/model.rb
+++ b/lib/groq/model.rb
@@ -49,5 +49,23 @@ def default_model
     def default_model_id
       default_model[:model_id]
     end
+
+    # https://api.groq.com/openai/v1/models
+    # Output:
+    # {"object": "list",
+    # "data": [
+    #     {
+    #         "id": "gemma-7b-it",
+    #         "object": "model",
+    #         "created": 1693721698,
+    #         "owned_by": "Google",
+    #         "active": true,
+    #         "context_window": 8192
+    #     },
+    def load_models(client:)
+      client ||= Groq::Client.new
+      response = client.get(path: "/openai/v1/models")
+      response.body
+    end
   end
 end
diff --git a/test/fixtures/vcr_cassettes/api/get_models.yml b/test/fixtures/vcr_cassettes/api/get_models.yml
new file mode 100644
index 0000000..617fdc1
--- /dev/null
+++ b/test/fixtures/vcr_cassettes/api/get_models.yml
@@ -0,0 +1,58 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://api.groq.com/openai/v1/models
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Faraday v2.9.0
+      Authorization:
+      - Bearer <GROQ_API_KEY>
+      Accept-Encoding:
+      - gzip;q=1.0,deflate;q=0.6,identity;q=0.3
+      Accept:
+      - "*/*"
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Date:
+      - Sat, 20 Apr 2024 20:56:50 GMT
+      Content-Type:
+      - application/json
+      Transfer-Encoding:
+      - chunked
+      Connection:
+      - keep-alive
+      Cache-Control:
+      - private, max-age=0, no-store, no-cache, must-revalidate
+      Vary:
+      - Origin, Accept-Encoding
+      X-Request-Id:
+      - req_01hvymr9mpf58vvv3r66m1p3y9
+      Via:
+      - 1.1 google
+      Alt-Svc:
+      - h3=":443"; ma=86400
+      Cf-Cache-Status:
+      - DYNAMIC
+      Set-Cookie:
+      - __cf_bm=1_7GmiVeiw0MZ7WgpYSjlt41aefHP9xwUc8hNvwwewE-1713646610-1.0.1.1-qULpGYO__MQhQfX5bCLhqzZ9nNP1GGW7tQRdYuE53yICW9WLOXFaA0swUiwE4hKBXeSU1UAr6M46BAcWjMuKJA;
+        path=/; expires=Sat, 20-Apr-24 21:26:50 GMT; domain=.groq.com; HttpOnly; Secure;
+        SameSite=None
+      Server:
+      - cloudflare
+      Cf-Ray:
+      - 87780b0fb8efa80e-SYD
+    body:
+      encoding: ASCII-8BIT
+      string: '{"object":"list","data":[{"id":"gemma-7b-it","object":"model","created":1693721698,"owned_by":"Google","active":true,"context_window":8192},{"id":"llama2-70b-4096","object":"model","created":1693721698,"owned_by":"Meta","active":true,"context_window":4096},{"id":"llama3-70b-8192","object":"model","created":1693721698,"owned_by":"Meta","active":true,"context_window":8192},{"id":"llama3-8b-8192","object":"model","created":1693721698,"owned_by":"Meta","active":true,"context_window":8192},{"id":"mixtral-8x7b-32768","object":"model","created":1693721698,"owned_by":"Mistral
+        AI","active":true,"context_window":32768}]}
+
+        '
+  recorded_at: Sat, 20 Apr 2024 20:56:49 GMT
+recorded_with: VCR 6.2.0
diff --git a/test/groq/test_models.rb b/test/groq/test_models.rb
new file mode 100644
index 0000000..9f2cc80
--- /dev/null
+++ b/test/groq/test_models.rb
@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+require "test_helper"
+
+class TestGroqModel < Minitest::Test
+  def test_load_models
+    VCR.use_cassette("api/get_models") do
+      client = Groq::Client.new
+      models = Groq::Model.load_models(client: client)
+      expected = {
+        "object" => "list",
+        "data" =>
+       [{"id" => "gemma-7b-it", "object" => "model", "created" => 1693721698, "owned_by" => "Google", "active" => true, "context_window" => 8192},
+         {"id" => "llama2-70b-4096", "object" => "model", "created" => 1693721698, "owned_by" => "Meta", "active" => true, "context_window" => 4096},
+         {"id" => "llama3-70b-8192", "object" => "model", "created" => 1693721698, "owned_by" => "Meta", "active" => true, "context_window" => 8192},
+         {"id" => "llama3-8b-8192", "object" => "model", "created" => 1693721698, "owned_by" => "Meta", "active" => true, "context_window" => 8192},
+         {"id" => "mixtral-8x7b-32768", "object" => "model", "created" => 1693721698, "owned_by" => "Mistral AI", "active" => true, "context_window" => 32768}]
+      }
+      assert_equal expected, models
+    end
+  end
+end