How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Gray Swan Cygnal API

The Cygnal API from Gray Swan — 7 operation(s) for cygnal.

Gray Swan Cygnal API is one of 3 APIs that Gray Swan publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

Tagged areas include Cygnal. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, and an API reference.

This API exposes 7 operations across 7 paths, and defines 49 schemas. It is described by OpenAPI 3.2.0, at version 0.1.0.

Requests are made against a single base URL, https://api.grayswan.ai.

7 operations 7 paths 49 schemas 7 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.1.0
Base URL
https://api.grayswan.ai
Resource Areas
1

Paths & Operations 7

Across 7 paths, the API surfaces 7 operations — 7 POST. Each is listed below with its method, path, parameters, and response codes.

Cygnal 7
POST
/cygnal/monitor
Cygnal Monitor
cygnal_monitor_cygnal_monitor_post body → 200400401422500
POST
/cygnal/chat/completions
Cygnal Completions
cygnal_completions_cygnal_chat_completions_post body → 200400401422500
POST
/cygnal/v1/chat/completions
Cygnal Completions
cygnal_completions_cygnal_v1_chat_completions_post body → 200400401422500
POST
/cygnal/v1/messages
Cygnal Anthropic Messages
cygnal_anthropic_messages_cygnal_v1_messages_post → 200400401422500
POST
/cygnal/v1beta/models/{model}:generateContent
Cygnal Gemini Generate
cygnal_gemini_generate_cygnal_v1beta_models__model__generateContent_post 1 param → 200400401422500
POST
/cygnal/v1beta/models/{model}:streamGenerateContent
Cygnal Gemini Stream Generate Content
cygnal_gemini_stream_generate_content_cygnal_v1beta_models__model__streamGenerateContent_post 1 param → 200400401422500
POST
/cygnal/responses
Cygnal Responses
cygnal_responses_cygnal_responses_post body → 200400401422500502

Schemas 49

The contract defines 49 schemas that model the data the API accepts and returns. The most detailed are CreateChatCompletionRequest (32 properties), CreateResponseRequest (29 properties), MonitoringResponse (15 properties), CreateMonitorRequest (11 properties). Each schema is shown below with its type and property counts.

api__types__responses__anthropic_response__CreateChatCompletionResponse
object
Anthropic message response
7 properties 5 required
ChatCompletionChoice
object
4 properties 3 required
PromptTokensDetails
object
Breakdown of tokens used in the prompt.
2 properties
ChatCompletionMessageFunctionToolCall
object
A call to a function tool created by the model.
3 properties 3 required
api__types__requests__openai_request__ToolFunction
object
4 properties 3 required
CompletionUsage
object
Usage statistics for the completion request.
5 properties 3 required
api__types__responses__openai_response__CreateChatCompletionResponse
object
Based on OpenAI's official Completion type
7 properties 5 required
MonitorMessage
object
5 properties 1 required
ResponseMessage
object
2 properties
ResponseChoice
object
3 properties
Conversation
object
1 property 1 required
MonitoringResponse
object
Response schema for monitoring/moderation results. Also used as the structure for preanalysis and postgenerationanalysis dicts in activity logging.
15 properties
GeminiGenerateContentResponse
object
4 properties 2 required
CreateResponseRequest
object
29 properties
RuleDescription
object
Schema for violated rule descriptions used in MonitoringResponse.
3 properties
ResponseUsage
object
5 properties
GeminiPromptFeedback
object
1 property
GeminiCandidate
object
5 properties 1 required
CreateMonitorRequest
object
11 properties
MonitorTool
object
SystemPromptScannerConfig
object
Configuration for the system prompt scanner.
1 property
GeminiContent
object
2 properties 1 required
Function
object
The function that the model called.
2 properties 2 required
ToolUseBlock
object
Tool use block for Anthropic responses
4 properties 4 required
JSONValue-Output
MonitorMessageRole
string
CreateChatCompletionRequest
object
32 properties 2 required
ToolChoiceName
object
1 property 1 required
ChatCompletionRequestMessage
object
4 properties 1 required
IgnoredInput
object
Schema for inputs intentionally excluded before moderation.
3 properties 3 required
AnthropicUsage
object
Usage information for Anthropic API
2 properties 2 required
PIIScannerConfig
object
Configuration for the PII scanner.
1 property
ResponseError
object
4 properties
ResponsesEndpointResponse
object
7 properties
GeminiStreamCandidate
object
2 properties 1 required
JSONValue-Input
CompletionTokensDetails
object
Breakdown of tokens used in a completion.
4 properties
ContentBlock-Output
object
Base content block for Anthropic responses
2 properties 2 required
GeminiUsageMetadata
object
3 properties
MonitorMessageContentPart
object
6 properties 1 required
GeminiStreamChunkResponse
object
1 property 1 required
GeminiSafetyRating
object
3 properties
Tool
object
2 properties 2 required
GeminiPart
object
1 property 1 required
Prompt
object
3 properties 1 required
ChatCompletionResponseMessage
object
3 properties 1 required
StandardErrorResponse
object
5 properties 2 required
JSONPrimitive
ToolChoice
object
2 properties 2 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

gray-swan-cygnal-api-openapi.yml Raw ↑

Other APIs Gray Swan publishes across the network.

Gray Swan Activity API
Gray Swan Policies API
Where this information came from

This is an independent, third-party profile of Gray Swan Cygnal 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.