Single turn

Multiple turns

Multimodal

Chat

Get Models

Models

A collection of pieces of content from a single entity (role).

ChatMessage

Type that represents a collection of turns from a single
entity (role). This is the streaming version.

ChatMessageChunk

ChatMessageChunkContentItem

ChatMessageInputContentItem

ChatMessageOutputContentItem

ChatResponse

What is the role of the particular turn. Supports turns from a person and
the model for now

ChatRole

Streaming specialisation of a chat response.

ChunkChatResponse

ChunkMessageResponse

Content

FinishReason

HTTPValidationError

MediaType

MessageResponse

Model

In conjunction with MediaType this is used to enforce the
{"type": "image_url", "image_url":"https://..."} spec.

Invariant: exactly the `type` url is not None

TypedMediaContent

Another way to specify a text message when you are sending multimodal input.
Your content might look something like that:

[
{"type": "text", "text":"What is the image?"},
{"type": "image_url", "image_url":"https://..."},
{"type": "text", "text":"Ignore the image and just write a Python script"}
]

1	[
2	{
3	"id": "reka-core"
4	},
5	{
6	"id": "reka-core-20240415"
7	},
8	{
9	"id": "reka-core-20240501"
10	},
11	{
12	"id": "reka-flash"
13	},
14	{
15	"id": "reka-flash-20240226"
16	},
17	{
18	"id": "reka-edge"
19	},
20	{
21	"id": "reka-edge-20240208"
22	}
23	]

1	curl https://api.reka.ai/v1/models \
2	-H "X-Api-Key: <apiKey>"