feat: DIA-1384: Estimate cost for an inference run

.mock/definition/__package__.yml

@@ -2347,6 +2347,19 @@ types:
       organization: optional<PromptVersionOrganization>
     source:
       openapi: openapi/openapi.yaml
+  InferenceRunCostEstimate:
+    properties:
+      prompt_cost_usd:
+        type: optional<string>
+        docs: Cost of the prompt (in USD)
+      completion_cost_usd:
+        type: optional<string>
+        docs: Cost of the completion (in USD)
+      total_cost_usd:
+        type: optional<string>
+        docs: Total cost of the inference (in USD)
+    source:
+      openapi: openapi/openapi.yaml
   RefinedPromptResponseRefinementStatus:
     enum:
       - Pending

.mock/definition/prompts/versions.yml

@@ -162,6 +162,51 @@ service:
               organization: 1
       audiences:
         - public
+    cost_estimate:
+      path: /api/prompts/{prompt_id}/versions/{version_id}/cost-estimate
+      method: POST
+      auth: true
+      docs: >
+        Get cost estimate for running a prompt version on a particular
+        project/subset
+      path-parameters:
+        prompt_id:
+          type: integer
+          docs: Prompt ID
+        version_id:
+          type: integer
+          docs: Prompt Version ID
+      display-name: >-
+        Get cost estimate for running a prompt version on a particular
+        project/subset
+      request:
+        name: VersionsCostEstimateRequest
+        query-parameters:
+          project_id:
+            type: integer
+            docs: ID of the project to get an estimate for running on
+          project_subset:
+            type: integer
+            docs: >-
+              Subset of the project to get an estimate for running on (e.g.
+              'All', 'Sample', or 'HasGT')
+      response:
+        docs: ''
+        type: root.InferenceRunCostEstimate
+      examples:
+        - path-parameters:
+            prompt_id: 1
+            version_id: 1
+          query-parameters:
+            project_id: 1
+            project_subset: 1
+          response:
+            body:
+              prompt_cost_usd: prompt_cost_usd
+              completion_cost_usd: completion_cost_usd
+              total_cost_usd: total_cost_usd
+      audiences:
+        - public
     get_refined_prompt:
       path: /api/prompts/{prompt_id}/versions/{version_id}/refine
       method: GET

reference.md

@@ -15161,6 +15161,103 @@ client.prompts.versions.update(
 </dl>
 
 
+</dd>
+</dl>
+</details>
+
+<details><summary><code>client.prompts.versions.<a href="src/label_studio_sdk/prompts/versions/client.py">cost_estimate</a>(...)</code></summary>
+<dl>
+<dd>
+
+#### 📝 Description
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+Get cost estimate for running a prompt version on a particular project/subset
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### 🔌 Usage
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+```python
+from label_studio_sdk.client import LabelStudio
+
+client = LabelStudio(
+    api_key="YOUR_API_KEY",
+)
+client.prompts.versions.cost_estimate(
+    prompt_id=1,
+    version_id=1,
+    project_id=1,
+    project_subset=1,
+)
+
+```
+</dd>
+</dl>
+</dd>
+</dl>
+
+#### ⚙️ Parameters
+
+<dl>
+<dd>
+
+<dl>
+<dd>
+
+**prompt_id:** `int` — Prompt ID
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**version_id:** `int` — Prompt Version ID
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**project_id:** `int` — ID of the project to get an estimate for running on
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**project_subset:** `int` — Subset of the project to get an estimate for running on (e.g. 'All', 'Sample', or 'HasGT')
+
+</dd>
+</dl>
+
+<dl>
+<dd>
+
+**request_options:** `typing.Optional[RequestOptions]` — Request-specific configuration.
+
+</dd>
+</dl>
+</dd>
+</dl>
+
+
 </dd>
 </dl>
 </details>

src/label_studio_sdk/__init__.py

@@ -35,6 +35,7 @@
     GcsImportStorage,
     GcsImportStorageStatus,
     InferenceRun,
+    InferenceRunCostEstimate,
     InferenceRunCreatedBy,
     InferenceRunOrganization,
     InferenceRunProjectSubset,
@@ -222,6 +223,7 @@
     "GcsImportStorageStatus",
     "ImportStorageListTypesResponseItem",
     "InferenceRun",
+    "InferenceRunCostEstimate",
     "InferenceRunCreatedBy",
     "InferenceRunOrganization",
     "InferenceRunProjectSubset",

src/label_studio_sdk/prompts/versions/client.py

@@ -9,6 +9,7 @@
 from ...core.jsonable_encoder import jsonable_encoder
 from ...core.pydantic_utilities import pydantic_v1
 from ...core.request_options import RequestOptions
+from ...types.inference_run_cost_estimate import InferenceRunCostEstimate
 from ...types.prompt_version import PromptVersion
 from ...types.prompt_version_created_by import PromptVersionCreatedBy
 from ...types.prompt_version_organization import PromptVersionOrganization
@@ -336,6 +337,68 @@ def update(
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    def cost_estimate(
+        self,
+        prompt_id: int,
+        version_id: int,
+        *,
+        project_id: int,
+        project_subset: int,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> InferenceRunCostEstimate:
+        """
+        Get cost estimate for running a prompt version on a particular project/subset
+
+        Parameters
+        ----------
+        prompt_id : int
+            Prompt ID
+
+        version_id : int
+            Prompt Version ID
+
+        project_id : int
+            ID of the project to get an estimate for running on
+
+        project_subset : int
+            Subset of the project to get an estimate for running on (e.g. 'All', 'Sample', or 'HasGT')
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        InferenceRunCostEstimate
+
+
+        Examples
+        --------
+        from label_studio_sdk.client import LabelStudio
+
+        client = LabelStudio(
+            api_key="YOUR_API_KEY",
+        )
+        client.prompts.versions.cost_estimate(
+            prompt_id=1,
+            version_id=1,
+            project_id=1,
+            project_subset=1,
+        )
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"api/prompts/{jsonable_encoder(prompt_id)}/versions/{jsonable_encoder(version_id)}/cost-estimate",
+            method="POST",
+            params={"project_id": project_id, "project_subset": project_subset},
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(InferenceRunCostEstimate, _response.json())  # type: ignore
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     def get_refined_prompt(
         self,
         prompt_id: int,
@@ -789,6 +852,68 @@ async def update(
             raise ApiError(status_code=_response.status_code, body=_response.text)
         raise ApiError(status_code=_response.status_code, body=_response_json)
 
+    async def cost_estimate(
+        self,
+        prompt_id: int,
+        version_id: int,
+        *,
+        project_id: int,
+        project_subset: int,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> InferenceRunCostEstimate:
+        """
+        Get cost estimate for running a prompt version on a particular project/subset
+
+        Parameters
+        ----------
+        prompt_id : int
+            Prompt ID
+
+        version_id : int
+            Prompt Version ID
+
+        project_id : int
+            ID of the project to get an estimate for running on
+
+        project_subset : int
+            Subset of the project to get an estimate for running on (e.g. 'All', 'Sample', or 'HasGT')
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        InferenceRunCostEstimate
+
+
+        Examples
+        --------
+        from label_studio_sdk.client import AsyncLabelStudio
+
+        client = AsyncLabelStudio(
+            api_key="YOUR_API_KEY",
+        )
+        await client.prompts.versions.cost_estimate(
+            prompt_id=1,
+            version_id=1,
+            project_id=1,
+            project_subset=1,
+        )
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"api/prompts/{jsonable_encoder(prompt_id)}/versions/{jsonable_encoder(version_id)}/cost-estimate",
+            method="POST",
+            params={"project_id": project_id, "project_subset": project_subset},
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                return pydantic_v1.parse_obj_as(InferenceRunCostEstimate, _response.json())  # type: ignore
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, body=_response.text)
+        raise ApiError(status_code=_response.status_code, body=_response_json)
+
     async def get_refined_prompt(
         self,
         prompt_id: int,

src/label_studio_sdk/types/__init__.py

@@ -34,6 +34,7 @@
 from .gcs_import_storage import GcsImportStorage
 from .gcs_import_storage_status import GcsImportStorageStatus
 from .inference_run import InferenceRun
+from .inference_run_cost_estimate import InferenceRunCostEstimate
 from .inference_run_created_by import InferenceRunCreatedBy
 from .inference_run_organization import InferenceRunOrganization
 from .inference_run_project_subset import InferenceRunProjectSubset
@@ -130,6 +131,7 @@
     "GcsImportStorage",
     "GcsImportStorageStatus",
     "InferenceRun",
+    "InferenceRunCostEstimate",
     "InferenceRunCreatedBy",
     "InferenceRunOrganization",
     "InferenceRunProjectSubset",

src/label_studio_sdk/types/inference_run_cost_estimate.py

@@ -0,0 +1,42 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import deep_union_pydantic_dicts, pydantic_v1
+
+
+class InferenceRunCostEstimate(pydantic_v1.BaseModel):
+    prompt_cost_usd: typing.Optional[str] = pydantic_v1.Field(default=None)
+    """
+    Cost of the prompt (in USD)
+    """
+
+    completion_cost_usd: typing.Optional[str] = pydantic_v1.Field(default=None)
+    """
+    Cost of the completion (in USD)
+    """
+
+    total_cost_usd: typing.Optional[str] = pydantic_v1.Field(default=None)
+    """
+    Total cost of the inference (in USD)
+    """
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults_exclude_unset: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        kwargs_with_defaults_exclude_none: typing.Any = {"by_alias": True, "exclude_none": True, **kwargs}
+
+        return deep_union_pydantic_dicts(
+            super().dict(**kwargs_with_defaults_exclude_unset), super().dict(**kwargs_with_defaults_exclude_none)
+        )
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}