added create endpoint with availability zone and list availability zones. still need to return availability zone per endpoint.

Author: atihkin

src/together/cli/api/endpoints.py

@@ -133,8 +133,8 @@ def endpoints(ctx: click.Context) -> None:
     help="Number of minutes of inactivity after which the endpoint will be automatically stopped. Set to 0 to disable.",
 )
 @click.option(
-    "--user-specified-avzone",
-    help="User-specified availability zone (e.g., us-central-4b)",
+    "--availability-zone",
+    help="Start endpoint in specified availability zone (e.g., us-central-4b)",
 )
 @click.option(
     "--wait",
@@ -156,7 +156,7 @@ def create(
     no_speculative_decoding: bool,
     no_auto_start: bool,
     inactive_timeout: int | None,
-    user_specified_avzone: str | None,
+    availability_zone: str | None,
     wait: bool,
 ) -> None:
     """Create a new dedicated inference endpoint."""
@@ -182,7 +182,7 @@ def create(
             disable_speculative_decoding=no_speculative_decoding,
             state="STOPPED" if no_auto_start else "STARTED",
             inactive_timeout=inactive_timeout,
-            user_specified_avzone=user_specified_avzone,
+            availability_zone=availability_zone,
         )
     except InvalidRequestError as e:
         print_api_error(e)
@@ -209,8 +209,8 @@ def create(
         click.echo("  Auto-start: disabled", err=True)
     if inactive_timeout is not None:
         click.echo(f"  Inactive timeout: {inactive_timeout} minutes", err=True)
-    if user_specified_avzone:
-        click.echo(f"  Availability zone: {user_specified_avzone}", err=True)
+    if availability_zone:
+        click.echo(f"  Availability zone: {availability_zone}", err=True)
 
     click.echo(f"Endpoint created successfully, id: {response.id}", err=True)
 
@@ -458,22 +458,24 @@ def update(
     click.echo("Successfully updated endpoint", err=True)
     click.echo(endpoint_id)
 
+
 @endpoints.command()
 @click.option("--json", is_flag=True, help="Print output in JSON format")
 @click.pass_obj
 @handle_api_errors
-def avzones(client: Together, json: bool) -> None:
-    """List all available availability zones."""
+def availability_zones(client: Together, json: bool) -> None:
+    """List all availability zones."""
     avzones = client.endpoints.list_avzones()
-    
+
     if not avzones:
         click.echo("No availability zones found", err=True)
         return
-    
+
     if json:
         import json as json_lib
+
         click.echo(json_lib.dumps({"avzones": avzones}, indent=2))
     else:
         click.echo("Available zones:", err=True)
-        for avzone in sorted(avzones):
-            click.echo(f"  {avzone}")
+        for availability_zone in sorted(avzones):
+            click.echo(f"  {availability_zone}")

src/together/resources/endpoints.py

@@ -76,7 +76,7 @@ def create(
         disable_speculative_decoding: bool = True,
         state: Literal["STARTED", "STOPPED"] = "STARTED",
         inactive_timeout: Optional[int] = None,
-        user_specified_avzone: Optional[str] = None,
+        availability_zone: Optional[str] = None,
     ) -> DedicatedEndpoint:
         """
         Create a new dedicated endpoint.
@@ -91,7 +91,7 @@ def create(
             disable_speculative_decoding (bool, optional): Whether to disable speculative decoding. Defaults to False.
             state (str, optional): The desired state of the endpoint. Defaults to "STARTED".
             inactive_timeout (int, optional): The number of minutes of inactivity after which the endpoint will be automatically stopped. Set to 0 to disable automatic timeout.
-            user_specified_avzone (str, optional): Start endpoint in specified availability zone (e.g., us-central-4b).
+            availability_zone (str, optional): Start endpoint in specified availability zone (e.g., us-central-4b).
 
         Returns:
             DedicatedEndpoint: Object containing endpoint information
@@ -118,8 +118,8 @@ def create(
         if inactive_timeout is not None:
             data["inactive_timeout"] = inactive_timeout
 
-        if user_specified_avzone is not None:
-            data["user_specified_avzone"] = user_specified_avzone
+        if availability_zone is not None:
+            data["availability_zone"] = availability_zone
 
         response, _, _ = requestor.request(
             options=TogetherRequest(
@@ -292,7 +292,7 @@ def list_avzones(self) -> List[str]:
         response, _, _ = requestor.request(
             options=TogetherRequest(
                 method="GET",
-                url="clusters/avzones",
+                url="clusters/availability-zones",
             ),
             stream=False,
         )
@@ -370,7 +370,7 @@ async def create(
         disable_speculative_decoding: bool = True,
         state: Literal["STARTED", "STOPPED"] = "STARTED",
         inactive_timeout: Optional[int] = None,
-        user_specified_avzone: Optional[str] = None,
+        availability_zone: Optional[str] = None,
     ) -> DedicatedEndpoint:
         """
         Create a new dedicated endpoint.
@@ -411,8 +411,8 @@ async def create(
         if inactive_timeout is not None:
             data["inactive_timeout"] = inactive_timeout
 
-        if user_specified_avzone is not None:
-            data["user_specified_avzone"] = user_specified_avzone
+        if availability_zone is not None:
+            data["availability_zone"] = availability_zone
 
         response, _, _ = await requestor.arequest(
             options=TogetherRequest(
@@ -575,7 +575,7 @@ async def list_hardware(
 
     async def list_avzones(self) -> List[str]:
         """
-        List all available availability zones.
+        List all availability zones.
 
         Returns:
             List[str]: List of unique availability zones
@@ -587,7 +587,7 @@ async def list_avzones(self) -> List[str]:
         response, _, _ = await requestor.arequest(
             options=TogetherRequest(
                 method="GET",
-                url="clusters/avzones",
+                url="clusters/availability-zones",
             ),
             stream=False,
         )
@@ -596,4 +596,4 @@ async def list_avzones(self) -> List[str]:
         assert isinstance(response.data, dict)
         assert isinstance(response.data["avzones"], list)
 
-        return response.data["avzones"]
+        return response.data["avzones"]