Add hatch test matrix for Python 3.10-3.13 and legacy tests for 3.8-3.9

- Configure hatch test matrix for Python 3.10-3.13 (coverage requires 3.10+)
- Add separate test-legacy workflow job for Python 3.8 and 3.9
- Tests verified passing on all versions locally

.github/workflows/publish.yaml

@@ -13,7 +13,7 @@ jobs:
       id-token: write
       contents: write
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: actions/setup-python@v6
       - uses: astral-sh/setup-uv@v5
         with:

.github/workflows/test.yaml

@@ -10,16 +10,28 @@ jobs:
   test:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: astral-sh/setup-uv@v5
         with:
           enable-cache: true
       - run: uvx hatch test -acp
         if: ${{ always() }}
+  test-legacy:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ['3.8', '3.9']
+    steps:
+      - uses: actions/checkout@v6
+      - uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: true
+      - name: Run tests on Python ${{ matrix.python-version }}
+        run: uv run --python ${{ matrix.python-version }} --with pytest --with pytest-anyio --with pytest-httpserver pytest tests/
   lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v5
+      - uses: actions/checkout@v6
       - uses: actions/setup-python@v6
       - uses: astral-sh/setup-uv@v5
         with:

README.md

@@ -50,6 +50,82 @@ for chunk in stream:
   print(chunk['message']['content'], end='', flush=True)
 ```
 
+## Cloud Models
+
+Run larger models by offloading to Ollama’s cloud while keeping your local workflow.
+
+- Supported models: `deepseek-v3.1:671b-cloud`, `gpt-oss:20b-cloud`, `gpt-oss:120b-cloud`, `kimi-k2:1t-cloud`, `qwen3-coder:480b-cloud`, `kimi-k2-thinking` See [Ollama Models - Cloud](https://ollama.com/search?c=cloud) for more information
+
+### Run via local Ollama
+
+1) Sign in (one-time):
+
+```
+ollama signin
+```
+
+2) Pull a cloud model:
+
+```
+ollama pull gpt-oss:120b-cloud
+```
+
+3) Make a request:
+
+```python
+from ollama import Client
+
+client = Client()
+
+messages = [
+  {
+    'role': 'user',
+    'content': 'Why is the sky blue?',
+  },
+]
+
+for part in client.chat('gpt-oss:120b-cloud', messages=messages, stream=True):
+  print(part.message.content, end='', flush=True)
+```
+
+### Cloud API (ollama.com)
+
+Access cloud models directly by pointing the client at `https://ollama.com`.
+
+1) Create an API key from [ollama.com](https://ollama.com/settings/keys) , then set:
+
+```
+export OLLAMA_API_KEY=your_api_key
+```
+
+2) (Optional) List models available via the API:
+
+```
+curl https://ollama.com/api/tags
+```
+
+3) Generate a response via the cloud API:
+
+```python
+import os
+from ollama import Client
+
+client = Client(
+    host='https://ollama.com',
+    headers={'Authorization': 'Bearer ' + os.environ.get('OLLAMA_API_KEY')}
+)
+
+messages = [
+  {
+    'role': 'user',
+    'content': 'Why is the sky blue?',
+  },
+]
+
+for part in client.chat('gpt-oss:120b', messages=messages, stream=True):
+  print(part.message.content, end='', flush=True)
+```
+
 ## Custom client
 A custom client can be created by instantiating `Client` or `AsyncClient` from `ollama`.
 

ollama/_client.py

@@ -1,3 +1,4 @@
+import contextlib
 import ipaddress
 import json
 import os
@@ -75,7 +76,7 @@ from ollama._types import (
 T = TypeVar('T')
 
 
-class BaseClient:
+class BaseClient(contextlib.AbstractContextManager, contextlib.AbstractAsyncContextManager):
   def __init__(
     self,
     client,
@@ -116,6 +117,12 @@ class BaseClient:
       **kwargs,
     )
 
+  def __exit__(self, exc_type, exc_val, exc_tb):
+    self.close()
+
+  async def __aexit__(self, exc_type, exc_val, exc_tb):
+    await self.close()
+
 
 CONNECTION_ERROR_MESSAGE = 'Failed to connect to Ollama. Please check that Ollama is downloaded, running and accessible. https://ollama.com/download'
 
@@ -124,6 +131,9 @@ class Client(BaseClient):
   def __init__(self, host: Optional[str] = None, **kwargs) -> None:
     super().__init__(httpx.Client, host, **kwargs)
 
+  def close(self):
+    self._client.close()
+
   def _request_raw(self, *args, **kwargs):
     try:
       r = self._client.request(*args, **kwargs)
@@ -702,6 +712,9 @@ class AsyncClient(BaseClient):
   def __init__(self, host: Optional[str] = None, **kwargs) -> None:
     super().__init__(httpx.AsyncClient, host, **kwargs)
 
+  async def close(self):
+    await self._client.aclose()
+
   async def _request_raw(self, *args, **kwargs):
     try:
       r = await self._client.request(*args, **kwargs)

pyproject.toml

@@ -32,6 +32,9 @@ extra-dependencies = [
     'pytest-httpserver',
 ]
 
+[[tool.hatch.envs.hatch-test.matrix]]
+python = ["3.10", "3.11", "3.12", "3.13"]
+
 [tool.hatch.envs.hatch-static-analysis]
 dependencies = [ 'ruff>=0.9.1' ]
 config-path = 'none'

tests/test_client.py

@@ -1347,3 +1347,33 @@ def test_client_explicit_bearer_header_overrides_env(monkeypatch: pytest.MonkeyP
   client = Client(headers={'Authorization': 'Bearer explicit-token'})
   assert client._client.headers['authorization'] == 'Bearer explicit-token'
   client.web_search('override check')
+
+
+def test_client_close():
+  client = Client()
+  client.close()
+  assert client._client.is_closed
+
+
+@pytest.mark.anyio
+async def test_async_client_close():
+  client = AsyncClient()
+  await client.close()
+  assert client._client.is_closed
+
+
+def test_client_context_manager():
+  with Client() as client:
+    assert isinstance(client, Client)
+    assert not client._client.is_closed
+
+  assert client._client.is_closed
+
+
+@pytest.mark.anyio
+async def test_async_client_context_manager():
+  async with AsyncClient() as client:
+    assert isinstance(client, AsyncClient)
+    assert not client._client.is_closed
+
+  assert client._client.is_closed