Skip to main content
POST
/
v3
/
compat
/
v1
/
messages
Messages API
curl --request POST \
  --url https://api.opper.ai/v3/compat/v1/messages \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "max_tokens": 123,
  "messages": [
    {
      "content": "<unknown>",
      "role": "<string>"
    }
  ],
  "model": "<string>"
}
'
{
  "content": [
    "<unknown>"
  ],
  "id": "<string>",
  "model": "<string>",
  "role": "<string>",
  "stop_reason": "<string>",
  "stop_sequence": "<string>",
  "type": "<string>",
  "usage": {
    "input_tokens": 123,
    "output_tokens": 123,
    "cache_creation_input_tokens": 123,
    "cache_read_input_tokens": 123,
    "server_tool_use": {}
  }
}

Authorizations

​
Authorization
string
header
required

API key authentication. Pass your API key as a Bearer token.

Headers

​
X-Opper-Name
string

Function name for tracing and routing.

​
X-Opper-Parent-Span-Id
string<uuid>

Parent span ID for distributed tracing context.

​
X-Opper-Guard-Input
string

Comma-separated input guardrail checks (e.g. "pii,secrets").

​
X-Opper-Guard-Output
string

Comma-separated output guardrail checks (e.g. "toxicity").

​
X-Opper-Guard-Action
enum<string>
default:flag

Action for guardrail violations: "flag" (default), "block", or "redact".

Available options:
flag,
block,
redact

Body

application/json
​
max_tokens
integer
required
​
messages
object[]
required
​
model
string
required
​
stop_sequences
string[]
​
stream
boolean
​
system
any

Any value

​
temperature
number
​
thinking
any

Any value

​
tool_choice
any

Any value

​
tools
object[]
​
top_k
integer
​
top_p
number

Response

Successful response

​
content
any[]
required

Any value

​
id
string
required
​
model
string
required
​
role
string
required
​
stop_reason
string
required
​
stop_sequence
string
required
​
type
string
required
​
usage
object
required