Skip to content
Nairon Docs

Chat Completions

POST
/v1/chat/completions
curl --request POST \
  --url https://example.com/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{ "model": "example", "messages": [ { "role": "example", "content": "example" } ], "stream": false, "reasoning": "turbo" }'

Authorizations

Section titled “Authorizations”

Request Bodyrequired

Section titled “Request Bodyrequired”
Media typeapplication/json
ChatCompletionRequest

OpenAI chat-completions-compatible; unknown fields pass through to the underlying model.

model accepts a catalogue tag (llm_models.tags) or "auto". reasoning is a Nairon-specific extension consulted only when model == "auto" — not passed through to the model.

object
model
required
Model
string
messages
required
Messages
Array<object>
ChatMessage

A single OpenAI chat message. content may be a string or a list of content-part objects (image/audio parts) — kept as Any and forwarded verbatim rather than re-modeled.

object
role
required
Role
string
content
Content
key
additional properties
any
stream
Stream
boolean
reasoning
Any of:
string
Allowed values: turbo fast balanced smart
key
additional properties
any

Responses

Section titled “Responses”

200

Section titled “200”

Successful Response

Media typeapplication/json
Examplegenerated
example

422

Section titled “422”

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{
  "detail": [
    {
      "loc": [
        "example"
      ],
      "msg": "example",
      "type": "example",
      "input": "example",
      "ctx": {}
    }
  ]
}