[Legacy] Create a Text Completion. The Text Completions API is a legacy API. We recommend using the [Messages API](https://d

Create a dict of type RequestOptions without keys of NotGiven values.

Get a specific model. The Models API response can be used to determine information about a specific model or resolve a model

List available models. The Models API response can be used to determine which models are available for use in the API. More

Close the response and release the connection. Automatically called if the response body is read to completion.

Wrapper over `transform()` that allows `None` to be passed. See `transform()` for more details.

Batches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a `canceling` state, at whi

Count the number of tokens in a Message. The Token Count API can be used to count the number of tokens in a Message, includi

Read and decode the JSON response content.

Loose coercion to the expected type with construction of nested values. If the given value does not match the expected type then it is returned a

Create a new client instance re-using the same options given to the current client with optional overriding.

Read and return the binary response content.

Recursively generate a dictionary representation of the model, optionally specifying which fields to include or exclude. By default, fields t

Higher order function that takes one of our bound API methods and wraps it to support streaming and returning the raw `APIResponse` object directl

Create a Message stream

Higher order function that takes one of our bound API methods and wraps it to support streaming and returning the raw `APIResponse` object directl

Wrapper over `async_transform()` that allows `None` to be passed. See `async_transform()` for more details.

Given a type like `Foo[T]`, returns the generic type variable `T`. This also handles the case where a concrete subclass is given, e.g. ```py

Streams the results of a Message Batch as a `.jsonl` file. Each line in the file is a JSON object containing the result of a single

Minimal reimplementation of copy.deepcopy() that will only copy certain object types: - mappings, e.g. `dict` - list This is done for pe

Given a type like `APIResponse[T]`, returns the generic type variable `T`. This also handles the case where a concrete subclass is given, e.g.

Waits until the stream has been read to completion and returns the accumulated `Message` object.

Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump_json Generates a JSON representation of the model using

A byte-iterator over the decoded response content. This automatically handles gzip, deflate and brotli encoded responses.

Usage docs: https://docs.pydantic.dev/2.4/concepts/serialization/#modelmodel_dump Generate a dictionary representation of the model, opti

Add a pydantic config for the given type. Note: this is a no-op on Pydantic v1.

Close the response and release the connection. Automatically called if the response body is read to completion.

Close the response and release the connection. Automatically called if the response body is read to completion.

Loose coercion to the expected type with construction of nested values. Note: the returned value from this function is not guaranteed to match th

Whether or not the response body has been closed. If this is False then there is response data that has not been read yet. You must e

Return whether the provided argument is an instance of `TypeAliasType`. ```python type Int = int is_type_alias_type(Int) # > True

Generates a JSON string representing this model as it would be received from or sent to the API (but with indentation). By default, fields th

If the given type is an `Annotated` type then it is returned, if not `None` is returned. This also unwraps the type when applicable, e.g. `Requir

Given an iterator that yields raw binary data, iterate over it & yield every event encountered

Close the underlying HTTPX client. The client will *not* be usable after this.

Create a new client instance re-using the same options given to the current client with optional overriding.

Recursively extract files from the given dictionary based on specified paths. A path may look like this ['foo', 'files', '<array>', 'data'].

Read and return the binary response content.