{
"id": "<string>",
"object": "chat.completion",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "system",
"content": "<string>",
"name": "<string>",
"tool_calls": [
{}
],
"tool_call_id": "<string>"
},
"finish_reason": "<string>"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"message": "Missing required agent id",
"type": "invalid_request_error",
"code": "missing_client_id"
}
}{
"error": {
"message": "Missing required template variables: appointment_time, city",
"type": "invalid_request_error",
"param": "template_variables",
"code": "missing_template_variables"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"param": "<string>",
"code": "missing_client_id"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"param": "<string>",
"code": "missing_client_id"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"param": "<string>",
"code": "missing_client_id"
}
}Create a chat completion
Route an OpenAI Chat Completions request. An agent ID and session ID are required, as
headers (X-Slng-Agent-Id, X-Slng-Session-Id) or body fields (slng_agent_id,
slng_session_id); the body field wins if both are sent.
{
"id": "<string>",
"object": "chat.completion",
"created": 123,
"model": "<string>",
"choices": [
{
"index": 123,
"message": {
"role": "system",
"content": "<string>",
"name": "<string>",
"tool_calls": [
{}
],
"tool_call_id": "<string>"
},
"finish_reason": "<string>"
}
],
"usage": {
"prompt_tokens": 123,
"completion_tokens": 123,
"total_tokens": 123
}
}{
"error": {
"message": "Missing required agent id",
"type": "invalid_request_error",
"code": "missing_client_id"
}
}{
"error": {
"message": "Missing required template variables: appointment_time, city",
"type": "invalid_request_error",
"param": "template_variables",
"code": "missing_template_variables"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"param": "<string>",
"code": "missing_client_id"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"param": "<string>",
"code": "missing_client_id"
}
}{
"error": {
"message": "<string>",
"type": "invalid_request_error",
"param": "<string>",
"code": "missing_client_id"
}
}Authorizations
Send your SLNG API key as a Bearer token (an OpenAI SDK's api_key option). Provider
credentials in slng_config authenticate to those providers.
Headers
Stable agent ID. Scopes the cache — change it when the system prompt changes. Required
unless sent as slng_agent_id (body wins). Max 256 chars; no whitespace, commas, pipes
or braces.
Opaque ID. Max 256 characters; no whitespace, commas, pipes or braces.
256^[^\s,|{}]+$ID for a single call, constant across its turns. Required unless sent as
slng_session_id (body wins). Same character rules as the agent ID.
Opaque ID. Max 256 characters; no whitespace, commas, pipes or braces.
256^[^\s,|{}]+$Optional correlation ID, echoed back in x-slng-request-id. X-Request-Id is also
accepted.
Body
OpenAI Chat Completions body plus SLNG extensions. Unlisted OpenAI fields pass through.
OpenAI messages array. template_variables substitution touches the system message only.
1Show child attributes
Show child attributes
slng/auto (or omit) answers from your configured models with failover, and picks
a tier for each request when you configure two or more tiers. Pass an entry's
model label to pin that model: no per-turn routing, no failover to another model,
and a separate cache. Any other value returns a 400.
"slng/auto"
"gpt-4o-mini"
OpenAI parameter, passed through.
OpenAI parameter, passed through.
OpenAI parameter, passed through.
OpenAI parameter, passed through.
true for SSE streaming, false for a single JSON response. Supported for every model.
Streaming options.
Show child attributes
Show child attributes
OpenAI tool definitions. Answers with tool calls, and the turn after a tool result, are not cached.
OpenAI tool choice, passed through.
SLNG extension. {name: value} map substituted into {{name}} placeholders in the
system message only. Names are letters, digits and underscore.
Limits (over any returns 422): 64 variables, 64-char names, 4000-char values. A
{{name}} with no value returns 422 (missing_template_variables); unused variables
are ignored.
Use for personalization that is spoken or echoed. Values that steer the answer (language, plan, region) belong in the prompt — steering here can make the cache serve another caller's answer.
Show child attributes
Show child attributes
{ "caller_name": "Rajesh", "city": "Mumbai" }
SLNG extension. Your models, endpoints and provider keys sent inline, applied on top of
the configuration your request uses (a project's key uses that project's). With
tiers, those models answer; without tiers, that configuration's models answer.
Settings you don't send come from that configuration; the fields you send apply to this
request only. The fields below are the ones most requests need: any other top-level
setting of the configuration can be sent the same way, and an unknown field returns 400.
Treat as a credential (HTTPS, keep out of logs); under 256 KB serialized. Invalid
config returns 400 (invalid slng_config:); a non-object returns 422
(invalid_slng_config).
Show child attributes
Show child attributes
Body form of X-Slng-Agent-Id. Required unless the header is sent; wins if both.
256^[^\s,|{}]+$Body form of X-Slng-Session-Id. Required unless the header is sent; wins if both.
256^[^\s,|{}]+$Set true to record the request and response (in-region) for analytics. Requires
both IDs.
Set true to return the provider response with no caching or edits. Failover still
applies. There is no per-turn tier pick: with two or more tiers, your default_tier
answers every turn, including turns that may need a tool call.
Response
Chat completion in OpenAI format, live or cached. See x-slng-response-source.