Class: Telnyx::Resources::AI::OpenAI

Inherits:
Object
  • Object
show all
Defined in:
lib/telnyx/resources/ai/openai.rb,
lib/telnyx/resources/ai/openai/chat.rb,
lib/telnyx/resources/ai/openai/embeddings.rb,
sig/telnyx/resources/ai/openai.rbs,
sig/telnyx/resources/ai/openai/chat.rbs,
sig/telnyx/resources/ai/openai/embeddings.rbs

Defined Under Namespace

Classes: Chat, Embeddings

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(client:) ⇒ OpenAI

This method is part of a private API. You should avoid using this method if possible, as it may be removed or be changed in the future.

Returns a new instance of OpenAI.

Parameters:



109
110
111
112
113
 
# File 'lib/telnyx/resources/ai/openai.rb', line 109

def initialize(client:)
  @client = client
  @embeddings = Telnyx::Resources::AI::OpenAI::Embeddings.new(client: client)
  @chat = Telnyx::Resources::AI::OpenAI::Chat.new(client: client)
end

Instance Attribute Details

#chat ⇒ Telnyx::Resources::AI::OpenAI::Chat (readonly)

Returns:



13
14
15
 
# File 'lib/telnyx/resources/ai/openai.rb', line 13

def chat
  @chat
end

#embeddings ⇒ Telnyx::Resources::AI::OpenAI::Embeddings (readonly)

OpenAI-compatible embeddings endpoints for generating vector representations of text

Returns:



10
11
12
 
# File 'lib/telnyx/resources/ai/openai.rb', line 10

def embeddings
  @embeddings
end

Instance Method Details

#create_response(conversation: nil, input: nil, instructions: nil, model: nil, stream: nil, request_options: {}) ⇒ Hash{Symbol=>Object}

Some parameter documentations has been truncated, see Models::AI::OpenAICreateResponseParams for more details.

Create a response using Telnyx's OpenAI-compatible Responses API. This endpoint is compatible with the OpenAI Responses API and may be used with the OpenAI JS or Python SDK by setting the base URL to https://api.telnyx.com/v2/ai/openai.

The conversation parameter refers to a Telnyx Conversation rather than an OpenAI-hosted conversation object. To persist a thread across turns, first create a conversation with POST /ai/conversations, then pass that conversation's id in the Responses request as conversation. The endpoint appends the new input, assistant output, reasoning, and tool-call messages to that conversation. Reuse the same conversation id on subsequent Responses requests, including tool-result followups, so the model receives the prior context.

If conversation is omitted, the request is processed without persisting messages to a Telnyx conversation. Use the Conversations API to manage history: list conversations (optionally filtered by metadata), fetch messages for a conversation, and optionally add messages outside the Responses flow.

You can attach arbitrary metadata when creating a conversation (for example to tag the conversation's source, channel, or user) and later filter by it when listing conversations.

Parameters:

  • conversation (String) —

    Optional Telnyx Conversation ID from POST /ai/conversations. When provided, Te

  • input (Hash{Symbol=>Object}) —

    The input items for this turn, using the OpenAI Responses API input format.

  • instructions (String) —

    Optional system/developer instructions for the model. When used with a persisted

  • model (String) —

    Model identifier to use for the response, for example zai-org/GLM-5.1-FP8 or a

  • stream (Boolean) —

    Set to true to stream Server-Sent Events, matching OpenAI's Responses streamin

  • request_options (Telnyx::RequestOptions, Hash{Symbol=>Object}, nil)

Returns:

  • (Hash{Symbol=>Object})

See Also:



63
64
65
66
67
68
69
70
71
72
 
# File 'lib/telnyx/resources/ai/openai.rb', line 63

def create_response(params = {})
  parsed, options = Telnyx::AI::OpenAICreateResponseParams.dump_request(params)
  @client.request(
    method: :post,
    path: "ai/openai/responses",
    body: parsed,
    model: Telnyx::Internal::Type::HashOf[Telnyx::Internal::Type::Unknown],
    options: options
  )
end

#list_models(request_options: {}) ⇒ Telnyx::Models::ModelsResponse

Lists every model currently available to your account on Telnyx Inference, including SOTA open-source LLMs hosted on Telnyx GPUs (for example moonshotai/Kimi-K2.6, zai-org/GLM-5.1-FP8, and MiniMaxAI/MiniMax-M2.7), embedding models, and any fine-tuned models you have created.

Each entry is a ModelMetadata object describing the model id, owner, task, context length, supported languages, billing tier, pricing per 1M tokens, deployment regions, and whether the model supports vision or fine-tuning. Use this endpoint to discover model ids you can pass to POST /v2/ai/openai/chat/completions.

Model ids follow the {organization}/{model_name} convention from Hugging Face (for example moonshotai/Kimi-K2.6). This endpoint is OpenAI-compatible: clients pointed at https://api.telnyx.com/v2/ai/openai can call client.models.list() to retrieve the same payload.

Parameters:

Returns:

See Also:



97
98
99
100
101
102
103
104
 
# File 'lib/telnyx/resources/ai/openai.rb', line 97

def list_models(params = {})
  @client.request(
    method: :get,
    path: "ai/openai/models",
    model: Telnyx::ModelsResponse,
    options: params[:request_options]
  )
end