API calls for all endpoints tagged CursorIntegration.
Summary
Functions
Anthropic complete (Cursor mount)
Cursor mount of the legacy Anthropic POST /v1/complete endpoint.
Anthropic count tokens (Cursor mount)
Cursor mount of POST /anthropic/v1/messages/count_tokens.
Anthropic messages (Cursor mount)
Cursor mount of POST /anthropic/v1/messages. Same request/response shape and streaming behaviour.
Anthropic messages — wildcard (Cursor mount)
Cursor mount of the Anthropic messages wildcard (POST /anthropic/v1/messages/{path}). Routes extended Anthropic messages endpoints (e.g. batches, count tokens) through Cursor.
Bedrock converse (Cursor mount)
Bedrock converse stream (Cursor mount)
Bedrock count tokens (Cursor mount)
Bedrock invoke (Cursor mount)
Bedrock invoke-with-response-stream (Cursor mount)
Bedrock rerank (Cursor mount)
Cursor hybrid chat completions
Accepts Cursor's hybrid chat-completions payload (which is structurally a Responses API request with input blocks) and returns a chat- completions-shaped response (choices + delta chunks for streams). Routes the request through the Responses pipeline internally.
Cohere chat (Cursor mount)
Cohere embed (Cursor mount)
Cohere rerank (Cursor mount)
Cohere tokenize (Cursor mount)
Gemini list models (Cursor mount)
Cursor mount of GET /genai/v1beta/models.
Gemini model action (Cursor mount)
Cursor mount of Gemini's wildcard generate-content/embed/count-tokens/ predict endpoints. The model path parameter includes the action suffix (e.g. gemini-pro:generateContent).
Gemini video operation polling (Cursor mount)
List models (Cursor)
Lists available models, returning the OpenAI /v1/models shape.
Vertex rank (Cursor mount)
Cursor mount of POST /genai/v1/rank — Vertex AI ranking.
Functions
@spec cursor_anthropic_complete( Tesla.Env.client(), ExBifrost.Model.AnthropicTextRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.AnthropicCreateComplete200Response.t()} | {:error, Tesla.Env.t()}
Anthropic complete (Cursor mount)
Cursor mount of the legacy Anthropic POST /v1/complete endpoint.
Parameters
connection(ExBifrost.Connection): Connection to serveranthropic_text_request(AnthropicTextRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.AnthropicCreateComplete200Response.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_anthropic_count_tokens( Tesla.Env.client(), ExBifrost.Model.AnthropicMessageRequest.t(), keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Anthropic count tokens (Cursor mount)
Cursor mount of POST /anthropic/v1/messages/count_tokens.
Parameters
connection(ExBifrost.Connection): Connection to serveranthropic_message_request(AnthropicMessageRequest):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_anthropic_messages( Tesla.Env.client(), ExBifrost.Model.AnthropicMessageRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.AnthropicCreateMessage400Response.t()} | {:ok, ExBifrost.Model.AnthropicMessageResponse.t()} | {:error, Tesla.Env.t()}
Anthropic messages (Cursor mount)
Cursor mount of POST /anthropic/v1/messages. Same request/response shape and streaming behaviour.
Parameters
connection(ExBifrost.Connection): Connection to serveranthropic_message_request(AnthropicMessageRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.AnthropicMessageResponse.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_anthropic_messages_wildcard( Tesla.Env.client(), String.t(), ExBifrost.Model.AnthropicMessageRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.AnthropicCreateMessage400Response.t()} | {:ok, ExBifrost.Model.AnthropicMessageResponse.t()} | {:error, Tesla.Env.t()}
Anthropic messages — wildcard (Cursor mount)
Cursor mount of the Anthropic messages wildcard (POST /anthropic/v1/messages/{path}). Routes extended Anthropic messages endpoints (e.g. batches, count tokens) through Cursor.
Parameters
connection(ExBifrost.Connection): Connection to serverpath(String.t):anthropic_message_request(AnthropicMessageRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.AnthropicMessageResponse.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_bedrock_converse( Tesla.Env.client(), String.t(), ExBifrost.Model.BedrockConverseRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.BedrockConverseResponse.t()} | {:error, Tesla.Env.t()}
Bedrock converse (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to servermodel_id(String.t):bedrock_converse_request(BedrockConverseRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.BedrockConverseResponse.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_bedrock_converse_stream( Tesla.Env.client(), String.t(), ExBifrost.Model.BedrockConverseRequest.t(), keyword() ) :: {:ok, String.t()} | {:error, Tesla.Env.t()}
Bedrock converse stream (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to servermodel_id(String.t):bedrock_converse_request(BedrockConverseRequest):opts(keyword): Optional parameters
Returns
{:ok, String.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_bedrock_count_tokens( Tesla.Env.client(), String.t(), ExBifrost.Model.CursorBedrockCountTokensRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.BedrockCountTokens200Response.t()} | {:error, Tesla.Env.t()}
Bedrock count tokens (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to servermodel_id(String.t):cursor_bedrock_count_tokens_request(CursorBedrockCountTokensRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.BedrockCountTokens200Response.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_bedrock_invoke( Tesla.Env.client(), String.t(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Bedrock invoke (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to servermodel_id(String.t):request_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_bedrock_invoke_stream( Tesla.Env.client(), String.t(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, String.t()} | {:error, Tesla.Env.t()}
Bedrock invoke-with-response-stream (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to servermodel_id(String.t):request_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, String.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_bedrock_rerank( Tesla.Env.client(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Bedrock rerank (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to serverrequest_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_chat_completions( Tesla.Env.client(), ExBifrost.Model.OpenAiResponsesRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.ChatCompletionResponse.t()} | {:ok, ExBifrost.Model.BifrostError.t()} | {:error, Tesla.Env.t()}
Cursor hybrid chat completions
Accepts Cursor's hybrid chat-completions payload (which is structurally a Responses API request with input blocks) and returns a chat- completions-shaped response (choices + delta chunks for streams). Routes the request through the Responses pipeline internally.
Parameters
connection(ExBifrost.Connection): Connection to serveropen_ai_responses_request(OpenAiResponsesRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.ChatCompletionResponse.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_cohere_chat( Tesla.Env.client(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Cohere chat (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to serverrequest_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_cohere_embed( Tesla.Env.client(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Cohere embed (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to serverrequest_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_cohere_rerank( Tesla.Env.client(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Cohere rerank (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to serverrequest_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_cohere_tokenize( Tesla.Env.client(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Cohere tokenize (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to serverrequest_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_gemini_list_models( Tesla.Env.client(), keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Gemini list models (Cursor mount)
Cursor mount of GET /genai/v1beta/models.
Parameters
connection(ExBifrost.Connection): Connection to serveropts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_gemini_model_action( Tesla.Env.client(), String.t(), ExBifrost.Model.GeminiGenerationRequest.t(), keyword() ) :: {:ok, ExBifrost.Model.GeminiGenerationResponse.t()} | {:error, Tesla.Env.t()}
Gemini model action (Cursor mount)
Cursor mount of Gemini's wildcard generate-content/embed/count-tokens/ predict endpoints. The model path parameter includes the action suffix (e.g. gemini-pro:generateContent).
Parameters
connection(ExBifrost.Connection): Connection to servermodel(String.t): Model name optionally followed by an action suffix.gemini_generation_request(GeminiGenerationRequest):opts(keyword): Optional parameters
Returns
{:ok, ExBifrost.Model.GeminiGenerationResponse.t}on success{:error, Tesla.Env.t}on failure
@spec cursor_gemini_retrieve_video_operation( Tesla.Env.client(), String.t(), String.t(), keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Gemini video operation polling (Cursor mount)
Parameters
connection(ExBifrost.Connection): Connection to servermodel(String.t):operation_id(String.t):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_list_models( Tesla.Env.client(), keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:ok, ExBifrost.Model.BifrostError.t()} | {:error, Tesla.Env.t()}
List models (Cursor)
Lists available models, returning the OpenAI /v1/models shape.
Parameters
connection(ExBifrost.Connection): Connection to serveropts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure
@spec cursor_vertex_rank( Tesla.Env.client(), %{optional(String.t()) => any()}, keyword() ) :: {:ok, %{optional(String.t()) => any()}} | {:error, Tesla.Env.t()}
Vertex rank (Cursor mount)
Cursor mount of POST /genai/v1/rank — Vertex AI ranking.
Parameters
connection(ExBifrost.Connection): Connection to serverrequest_body(%{optional(String.t) => any()}):opts(keyword): Optional parameters
Returns
{:ok, %{}}on success{:error, Tesla.Env.t}on failure