Pryon Generative API
The Generative API from Pryon — 6 operation(s) for generative.
Pryon Generative API is one of 24 APIs that Pryon publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Generative. The published artifact set on APIs.io includes an OpenAPI specification.
This API exposes 6 operations across 6 paths, and defines 183 schemas. It is described by OpenAPI 3.2.0, at version 1.0.
Requests are made against 2 base URLs: {pryon_base_url}, /.
6 operations
6 paths
183 schemas
1 GET5 POST
Metadata
The identity and technical contract details declared by the specification.
Paths & Operations 6
Across 6 paths, the API surfaces 6 operations — 1 GET, 5 POST. Each is listed below with its method, path, parameters, and response codes.
Generative 6
POST
/api/generative/v1alpha1/chat/completions
Chat Completions
GET
/api/generative/v1alpha1/chat/completions/models
Lists the models available for our Chat Completions API
POST
/api/generative/v1alpha1/tasks/complete-query
Generates a completed query by replacing references to entities / information in prior turns of the conversation.
POST
/api/generative/v1alpha1/tasks/guardrail-query
Return query toxicity and prompt injection classifications given a query
POST
/api/generative/v1alpha1/tasks/route-query
Return query out-of-domain classifications given a query
POST
/api/generative/v1alpha1/tasks/summarize-answer
Generates a summarized answer given retrieval outputs and configs
Schemas 183
The contract defines 183 schemas that model the data the API accepts and returns. The most detailed are ChatCompletionsRequest_7 (12 properties), ChatCompletionsRequest (12 properties), ChatCompletionsRequest_3 (11 properties), ExchangeOutput_2 (11 properties). Each schema is shown below with its type and property counts.
QueryGuardrailsRequest
object
1 property
ExchangeOutput
object
11 properties
Status
object
The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](h…
3 properties
FunctionDefinition
object
Function definition matching OpenAI's FunctionDefinition
4 properties
Choice
object
Individual completion choice.
5 properties
LogProbToken
object
3 properties
ChatCompletionsRequest
object
12 properties
Tool
object
Tool definition for function calling.
2 properties
DeltaToolCall
object
Tool call in assistant messages; for streamed responses.
4 properties
Attachment
object
2 properties
ListChatCompletionsModelsResponse
object
Response for ListChatCompletionsModels Provides all the available models for our Chat Completions API
1 property
Delta
object
Delta of a message for streaming.
3 properties
Message
object
Individual message in the conversation.
4 properties
RouteQueryRequest
object
3 properties
FunctionCall
object
Function call details
2 properties
LogProbs
object
2 properties
ChatCompletionsResponse
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
GoogleProtobufValue
Represents a dynamically typed value which can be either null, a number, a string, a boolean, a recursive struct value, or a list of values.
ListChatCompletionsModelsRequest
object
The request schema for our ListChatCompletionsModels endpoint
1 property
Usage
object
3 properties
MetadataTypeValue
object
3 properties
GenerationConfigs
object
6 properties
QueryGuardrailsResponse
object
2 properties
Context
object
1 property
ToolCall
object
Tool call in assistant messages (for responses).
3 properties
ChatCompletionsModels
object
A list of our Chat Completions models
1 property
CompleteQueryResponse
object
1 property
AnswerSummarizationConfigs
object
Answer summarization specific configurations
2 properties
ExchangeAudioOutput
object
4 properties
AttributionReference
object
Attribution reference
2 properties
JsonSchema
object
JSON Schema for structured outputs.
4 properties
LogProbTokenWithTop
object
4 properties
ChatCompletionsModel
object
An individual Chat Completions model.
2 properties
AnswerSummarizationRequest
object
5 properties
AnswerSummarizationResponse
object
6 properties
CompleteQueryRequest
object
3 properties
RouteQueryResponse
object
4 properties
GoogleProtobufAny
object
Contains an arbitrary serialized message along with a @type that describes the type of the serialized message.
1 property
ResponseFormat
object
Specifies the response format.
2 properties
QueryGuardrailsRequest_2
object
1 property
ChatCompletionsModel_2
object
An individual Chat Completions model
2 properties
RouteQueryResponse_2
object
4 properties
ListChatCompletionsModelsRequest_2
object
The request schema for our ListChatCompletionsModels endpoint.
1 property
QueryGuardrailsRequest_3
object
1 property
FunctionDefinition_2
object
Function definition; matches the OpenAI function definition.
4 properties
Choice_2
object
Individual completion choice
5 properties
LogProbToken_2
object
3 properties
ChatCompletionsRequest_2
object
11 properties
Tool_2
object
Tool definition for function calling
2 properties
DeltaToolCall_2
object
Tool call in assistant messages (for streamed responses)
4 properties
Delta_2
object
3 properties
Message_2
object
4 properties
FunctionCall_2
object
Function call details.
2 properties
ChatCompletionsResponse_2
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
GoogleProtobufValue_2
Tool used by the model to call the functions; valid values are auto (default; model decides whether to call a function and which one to use), none (model will…
Usage_2
object
3 properties
ToolCall_2
object
Tool call in assistant messages (for responses).
3 properties
LogProbTokenWithTop_2
object
4 properties
ChatCompletionsModel_3
object
An individual Chat Completions model
2 properties
RouteQueryResponse_3
object
4 properties
ListChatCompletionsModelsRequest_3
object
The request schema for our ListChatCompletionsModels endpoint.
1 property
v1alpha1ChatCompletionsResponse
object
6 properties
protobufAny
object
2 properties
v1alpha1CompleteQueryRequest
object
3 properties
v1alpha1LogProbToken
object
3 properties
v1alpha1Choice
object
5 properties
v1alpha1LogProbs
object
2 properties
v1alpha1ChatCompletionsRequest
object
9 properties
rpcStatus
object
3 properties
v1alpha1RouteQueryResponse
object
4 properties
v1alpha1Usage
object
3 properties
v1alpha1LogProbTokenWithTop
object
4 properties
v1alpha1Delta
object
2 properties
v1alpha1RouteQueryRequest
object
3 properties
v1alpha1CompleteQueryResponse
object
1 property
v1alpha1Message
object
2 properties
QueryGuardrailsRequest_4
object
1 property
ExchangeOutput_2
object
11 properties
FunctionDefinition_3
object
Function definition matching OpenAI's FunctionDefinition
4 properties
Choice_3
object
Individual completion choice
5 properties
LogProbToken_3
object
3 properties
ChatCompletionsRequest_3
object
11 properties
Tool_3
object
Tool definition for function calling
2 properties
DeltaToolCall_3
object
Tool call in assistant messages (for streamed responses)
4 properties
Attachment_2
object
2 properties
Delta_3
object
Delta of a message for streaming
3 properties
Message_3
object
Individual message in the conversation
4 properties
FunctionCall_3
object
Function call details
2 properties
ChatCompletionsResponse_3
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
Usage_3
object
Usage statistics TODO: if we're going out to reasoning models, do we need to include those tokens separately?
3 properties
GenerationConfigs_2
object
6 properties
Context_2
object
1 property
ToolCall_3
object
Tool call in assistant messages (for responses)
3 properties
AnswerSummarizationConfigs_2
object
2 properties
ExchangeAudioOutput_2
object
4 properties
AttributionReference_2
object
Attribution reference
2 properties
LogProbTokenWithTop_3
object
4 properties
ChatCompletionsModel_4
object
An individual Chat Completions model
2 properties
AnswerSummarizationRequest_2
object
5 properties
AnswerSummarizationResponse_2
object
6 properties
RouteQueryResponse_4
object
4 properties
Status_2
object
The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](h…
3 properties
Choice_4
object
Individual completion choice
5 properties
LogProbToken_4
object
3 properties
ChatCompletionsRequest_4
object
9 properties
ListChatCompletionsModelsResponse_2
object
Response for ListChatCompletionsModels Provides all the available models for our Chat Completions API
1 property
Delta_4
object
Delta of a message for streaming
2 properties
Message_4
object
Individual message in the conversation
2 properties
RouteQueryRequest_2
object
3 properties
ChatCompletionsResponse_4
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
Usage_4
object
Usage statistics TODO: if we're going out to reasoning models, do we need to include those tokens separately?
3 properties
ChatCompletionsModels_2
object
1 property
CompleteQueryResponse_2
object
1 property
LogProbTokenWithTop_4
object
4 properties
ChatCompletionsModel_5
object
An individual Chat Completions model
2 properties
CompleteQueryRequest_2
object
3 properties
RouteQueryResponse_5
object
4 properties
GoogleProtobufAny_2
object
Contains an arbitrary serialized message along with a @type that describes the type of the serialized message.
1 property
ListChatCompletionsModelsRequest_4
object
The request schema for our ListChatCompletionsModels endpoint
ChatCompletionsResponse_5
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
LogProbs_2
object
2 properties
LogProbTokenWithTop_5
object
4 properties
ChatCompletionsModels_3
object
A list of our Chat Completions models.
1 property
Usage_5
object
3 properties
ChatCompletionsModel_6
object
An individual Chat Completions model
2 properties
2 required
Choice_5
object
Individual completion choice
5 properties
ListChatCompletionsModelsResponse_3
object
Response for ListChatCompletionsModels Provides all the available models for our Chat Completions API
1 property
LogProbToken_5
object
3 properties
ChatCompletionsRequest_5
object
9 properties
Delta_5
object
2 properties
Message_5
object
Individual message in the conversation.
2 properties
ListChatCompletionsModelsRequest_5
object
The request schema for our ListChatCompletionsModels endpoint
QueryGuardrailsRequest_5
object
1 property
Status_3
object
The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](h…
3 properties
FunctionDefinition_4
object
Function definition matching OpenAI's FunctionDefinition
4 properties
Choice_6
object
Individual completion choice
5 properties
LogProbToken_6
object
3 properties
ChatCompletionsRequest_6
object
11 properties
Tool_4
object
Tool definition for function calling
2 properties
DeltaToolCall_4
object
Tool call in assistant messages (for streamed responses)
4 properties
Delta_6
object
Delta of a message for streaming
3 properties
Message_6
object
Individual message in the conversation
4 properties
RouteQueryRequest_3
object
3 properties
FunctionCall_4
object
Function call details
2 properties
ChatCompletionsResponse_6
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
Usage_6
object
Usage statistics TODO: if we're going out to reasoning models, do we need to include those tokens separately?
3 properties
QueryGuardrailsResponse_2
object
2 properties
ToolCall_4
object
Tool call in assistant messages (for responses)
3 properties
LogProbTokenWithTop_6
object
4 properties
ChatCompletionsModel_7
object
An individual Chat Completions model
2 properties
RouteQueryResponse_6
object
4 properties
GoogleProtobufAny_3
object
Contains an arbitrary serialized message along with a @type that describes the type of the serialized message.
1 property
ListChatCompletionsModelsRequest_6
object
The request schema for our ListChatCompletionsModels endpoint
QueryGuardrailsRequest_6
object
2 properties
FunctionDefinition_5
object
Function definition matching OpenAI's FunctionDefinition
4 properties
Choice_7
object
Individual completion choice
5 properties
LogProbToken_7
object
3 properties
ChatCompletionsRequest_7
object
12 properties
Tool_5
object
Tool definition for function calling
2 properties
DeltaToolCall_5
object
Tool call in assistant messages (for streamed responses)
4 properties
Delta_7
object
Delta of a message for streaming
3 properties
Message_7
object
Individual message in the conversation
4 properties
FunctionCall_5
object
Function call details
2 properties
ChatCompletionsResponse_7
object
Response for chat completion non-streaming: https://platform.openai.com/docs/api-reference/chat/object streaming: https://platform.openai.com/docs/api-referenc…
6 properties
Usage_7
object
Usage statistics TODO: if we're going out to reasoning models, do we need to include those tokens separately?
3 properties
GenerationConfigs_3
object
6 properties
ToolCall_5
object
Tool call in assistant messages (for responses)
3 properties
CompleteQueryResponse_3
object
1 property
ConversationMessage
object
Chat history structured conversation turns
2 properties
AnswerSummarizationConfigs_3
object
Answer summarization specific configurations
2 properties
ExchangeAudioOutput_3
object
4 properties
JsonSchema_2
object
JSON Schema for structured outputs
4 properties
LogProbTokenWithTop_7
object
4 properties
ChatCompletionsModel_8
object
An individual Chat Completions model
2 properties
AnswerSummarizationRequest_3
object
5 properties
CompleteQueryRequest_3
object
5 properties
RouteQueryResponse_7
object
4 properties
ResponseFormat_2
object
Response format specification
2 properties
v1alpha1CompleteQueryRequest_2
object
3 properties
v1alpha1RouteQueryResponse_2
object
4 properties
v1alpha1RouteQueryRequest_2
object
3 properties
v1alpha1RouteQueryResponse_3
object
4 properties
v1alpha1RouteQueryRequest_3
object
3 properties
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Pryon 12
Other APIs Pryon publishes across the network.
Pryon Analytics API
Pryon Connector Service External API
Pryon Content Service API
Pryon Content Service API
Pryon Exchange API
Pryon Exchange Event API
Pryon Feedback API
Pryon Generative Exchange API
Pryon Generative Feedback API
Pryon Generative Retrieval API
Pryon Generative Retrieval Feedback API
Pryon Knowledge Collection Service API
#Generative
Where this information came from
This is an independent, third-party profile of Pryon Generative API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.