diff --git a/docs/blog/posts/together.md b/docs/blog/posts/together.md
new file mode 100644
index 0000000..d5f1ed2
--- /dev/null
+++ b/docs/blog/posts/together.md
@@ -0,0 +1,86 @@
+---
+draft: False
+date: 2024-01-27
+slug: together
+tags:
+  - patching
+  - open source
+authors:
+  - jxnl
+---
+
+# Structured Outputs with Together AI
+
+Open-source LLMS are gaining popularity, and with the release of Together's Function calling models, its been easier than ever to get structured outputs.
+
+By the end of this blog post, you will learn how to effectively utilize instructor with Together AI. But before we proceed, let's first explore the concept of patching.
+
+!!! note "Other Languages"
+
+    This blog post is written in Python, but the concepts are applicable to other languages as well, as we currently have support for [Javascript](
+        https://instructor-ai.github.io/instructor-js) and [Elixir](https://hexdocs.pm/instructor/Instructor.html)
+
+<!-- more -->
+
+## Patching
+
+Instructor's patch enhances the openai api it with the following features:
+
+- `response_model` in `create` calls that returns a pydantic model
+- `max_retries` in `create` calls that retries the call if it fails by using a backoff strategy
+
+!!! note "Learn More"
+
+    To learn more, please refer to the [docs](../../index.md). To understand the benefits of using Pydantic with Instructor, visit the tips and tricks section of the [why use Pydantic](../../why.md) page.
+
+## Together AI
+
+The good news is that Together employs the same OpenAI client, and its models support some of these output modes too!
+
+!!! note "Getting access"
+
+    If you want to try this out for yourself check out the [Together AI](https://www.together.ai/) website. You can get started [here](http://api.together.ai/).
+
+```python
+import os
+import openai
+from pydantic import BaseModel
+import instructor
+
+client = openai.OpenAI(
+    base_url="https://api.together.xyz/v1",
+    api_key=os.environ["TOGETHER_API_KEY"],
+)
+
+
+# By default, the patch function will patch the ChatCompletion.create and ChatCompletion.create methods to support the response_model parameter
+client = instructor.patch(client, mode=instructor.Mode.TOOLS)
+
+
+# Now, we can use the response_model parameter using only a base model
+# rather than having to use the OpenAISchema class
+class UserExtract(BaseModel):
+    name: str
+    age: int
+
+
+user: UserExtract = client.chat.completions.create(
+    model="mistralai/Mixtral-8x7B-Instruct-v0.1",
+    response_model=UserExtract,
+    messages=[
+        {"role": "user", "content": "Extract jason is 25 years old"},
+    ],
+)
+
+assert isinstance(user, UserExtract), "Should be instance of UserExtract"
+assert user.name.lower() == "jason"
+assert user.age == 25
+
+print(user.model_dump_json(indent=2))
+{
+    "name": "Jason",
+    "age": 25,
+}
+```
+
+You can find more information about Together's function calling support [here](https://docs.together.ai/docs/function-calling).
diff --git a/examples/patching/anyscale.py b/examples/patching/anyscale.py
new file mode 100644
index 0000000..d4e7785
--- /dev/null
+++ b/examples/patching/anyscale.py
@@ -0,0 +1,37 @@
+import os
+import instructor
+
+from openai import OpenAI
+from pydantic import BaseModel
+
+
+# By default, the patch function will patch the ChatCompletion.create and ChatCompletion.acreate methods. to support response_model parameter
+client = instructor.patch(
+    OpenAI(
+        base_url="https://api.endpoints.anyscale.com/v1",
+        api_key=os.environ["ANYSCALE_API_KEY"],
+    ),
+    mode=instructor.Mode.JSON_SCHEMA,
+)
+
+
+# Now, we can use the response_model parameter using only a base model
+# rather than having to use the OpenAISchema class
+class UserExtract(BaseModel):
+    name: str
+    age: int
+
+
+user: UserExtract = client.chat.completions.create(
+    model="mistralai/Mixtral-8x7B-Instruct-v0.1",
+    response_model=UserExtract,
+    messages=[
+        {"role": "user", "content": "Extract jason is 25 years old"},
+    ],
+)  # type: ignore
+
+print(user)
+{
+    "name": "Jason",
+    "age": 25,
+}
diff --git a/examples/patching/patching.py b/examples/patching/oai.py
similarity index 88%
rename from examples/patching/patching.py
rename to examples/patching/oai.py
index 728b60c..205e9bf 100644
--- a/examples/patching/patching.py
+++ b/examples/patching/oai.py
@@ -1,3 +1,4 @@
+import os
 import instructor
 
 from openai import OpenAI
@@ -5,7 +6,10 @@ from pydantic import BaseModel
 
 
 # By default, the patch function will patch the ChatCompletion.create and ChatCompletion.acreate methods. to support response_model parameter
-client = instructor.patch(OpenAI())
+client = instructor.patch(
+    OpenAI(),
+    mode=instructor.Mode.TOOLS,
+)
 
 
 # Now, we can use the response_model parameter using only a base model
diff --git a/examples/patching/together.py b/examples/patching/together.py
new file mode 100644
index 0000000..c6bbb07
--- /dev/null
+++ b/examples/patching/together.py
@@ -0,0 +1,35 @@
+import os
+import openai
+from pydantic import BaseModel
+import instructor
+
+client = openai.OpenAI(
+    base_url="https://api.together.xyz/v1",
+    api_key=os.environ["TOGETHER_API_KEY"],
+)
+
+
+# By default, the patch function will patch the ChatCompletion.create and ChatCompletion.acreate methods. to support response_model parameter
+client = instructor.patch(client, mode=instructor.Mode.TOOLS)
+
+
+# Now, we can use the response_model parameter using only a base model
+# rather than having to use the OpenAISchema class
+class UserExtract(BaseModel):
+    name: str
+    age: int
+
+
+user: UserExtract = client.chat.completions.create(
+    model="mistralai/Mixtral-8x7B-Instruct-v0.1",
+    response_model=UserExtract,
+    messages=[
+        {"role": "user", "content": "Extract jason is 25 years old"},
+    ],
+)  # type: ignore
+
+print(user.model_dump_json(indent=2))
+{
+    "name": "Jason",
+    "age": 25,
+}
diff --git a/tests/__init__.py b/tests/__init__.py
deleted file mode 100644
index e69de29..0000000