Cygnal OpenAI Chat Completions

Authorization

AuthorizationBearer <token>

API Key

In: header

Request Body

messagesMessages

modelModel

metadata?Metadata

frequency_penalty?Frequency Penalty

logit_bias?Logit Bias

logprobs?Logprobs

top_logprobs?Top Logprobs

max_tokens?Max Tokens

max_completion_tokens?Max Completion Tokens

modalities?Modalities

n?N

Default1

prediction?Prediction

audio?Audio

presence_penalty?Presence Penalty

response_format?Response Format

seed?Seed

service_tier?Service Tier

stop?Stop

store?Store

stream?Stream

Defaultfalse

stream_options?Stream Options

temperature?Temperature

Default1

top_p?Top P

Default1

tools?Tools

tool_choice?Tool Choice

Default"auto"

parallel_tool_calls?Parallel Tool Calls

user?User

monitor_details?Monitor Details

policy_id?Policy Id

function_call?Function Call

functions?Functions

moderate_before?Moderate Before

Defaultfalse

Response Body

curl -X POST "https://api.grayswan.ai/cygnal/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "I need you to help me with something."
      }
    ],
    "stream": false,
    "temperature": 0.7,
    "max_tokens": 1000
  }'

curl -X POST "https://api.grayswan.ai/cygnal/chat/completions" \  -H "Content-Type: application/json" \  -d '{    "model": "gpt-4",    "messages": [      {        "role": "system",        "content": "You are a helpful assistant."      },      {        "role": "user",        "content": "I need you to help me with something."      }    ],    "stream": false,    "temperature": 0.7,    "max_tokens": 1000  }'

null

{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string"
    }
  ]
}

Cygnal OpenAI Chat Completions

Authorization

Request Body

Response Body

200

422