Chat Completion API

The Sequrity Control Chat Completion API is compatible with the OpenAI Chat Completions API. This allows you to use Sequrity's security features while maintaining compatibility with existing OpenAI-based applications.

For the Anthropic Messages format, see the Messages API reference.

Endpoints

Endpoint	Provider
POST /control/{endpoint_type}/v1/chat/completions	Default
POST /control/{endpoint_type}/openai/v1/chat/completions	OpenAI
POST /control/{endpoint_type}/openrouter/v1/chat/completions	OpenRouter
POST /control/{endpoint_type}/sequrity_azure/v1/chat/completions	Sequrity Azure

Where {endpoint_type} is chat, code, agent, or lang-graph. See URL Pattern and Service Providers.

Request Body

Field	Type	Required	Description
messages	array[Message]	Yes	A list of messages comprising the conversation so far. See Message Types.
model	string	Yes	Model ID, e.g. openai/gpt-5-mini. For Dual-LLM, specify two models separated by a comma (pllm,qllm).
temperature	float	No	Sampling temperature (0–2). Higher values produce more random output.
top_p	float	No	Nucleus sampling threshold. Use 0.1 for top 10% probability mass.
tools	array[Tool]	No	Tools the model may call. See Tools.
stream	boolean	No	If true, partial deltas are sent as server-sent events.
seed	integer	No	Seed for deterministic sampling (best-effort).
reasoning_effort	string	No	Reasoning effort for reasoning models: "none", "minimal", "low", "medium", "high", "xhigh".
response_format	object	No	Output format constraint. See Response Format.

Message Types

Messages are distinguished by the role field.

System Message

Field	Type	Required	Description
role	"system"	Yes
content	string | array[ContentPartText]	Yes	The system prompt.
name	string	No	Optional participant name.

Developer Message

Field	Type	Required	Description
role	"developer"	Yes
content	string | array[ContentPartText]	Yes	The developer message.
name	string	No	Optional participant name.

User Message

Field	Type	Required	Description
role	"user"	Yes
content	string | array[ContentPart]	Yes	Supports text, images, audio, and files. See Content Parts.
name	string	No	Optional participant name.

Assistant Message

Field	Type	Required	Description
role	"assistant"	Yes
content	string | array[ContentPartText | ContentPartRefusal] | null	No	Required unless tool_calls is specified.
name	string	No	Optional participant name.
refusal	string	No	Refusal message by the assistant.
audio	object	No	Reference to a previous audio response.
tool_calls	array[ToolCall]	No	Tool calls generated by the model.

Tool Message

Field	Type	Required	Description
role	"tool"	Yes
content	string | array[ContentPartText]	Yes	The tool result.
tool_call_id	string	Yes	ID of the tool call this responds to.

Content Parts

User messages support multimodal content:

Type	Key Fields	Description
text	type, text	Plain text.
image_url	type, image_url.url, image_url.detail	Image via URL or base64. Detail: "auto", "low", "high".
input_audio	type, input_audio.data, input_audio.format	Audio as base64. Format: "wav", "mp3".
file	type, file.file_data, file.file_id, file.filename	File via base64 or file ID.

Tools

Field	Type	Required	Description
type	"function"	Yes	Currently only "function" is supported.
function.name	string	Yes	Function name (a-z, A-Z, 0-9, underscores, dashes; max 64 chars).
function.description	string	No	What the function does.
function.parameters	object	No	JSON Schema describing the function parameters.
function.strict	boolean	No	Enable strict schema adherence.

Response Format

Type	Description
text	Default text response.
json_object	JSON mode — model outputs valid JSON.
json_schema	Structured Outputs with a JSON Schema. Fields: name, description, schema, strict.

Response Body

Field	Type	Description
id	string	Unique identifier for the chat completion.
object	"chat.completion"	Always "chat.completion".
created	integer	Unix timestamp (seconds) when created.
model	string	The model used.
choices	array[Choice]	Completion choices.
usage	CompletionUsage	Token usage statistics.
service_tier	string | null	Service tier used (e.g., "auto", "default", "flex", "scale", "priority").
system_fingerprint	string | null	Backend configuration fingerprint.

Choice

Field	Type	Description
index	integer	Index of this choice.
message	ResponseMessage	The generated message.
finish_reason	string	Why generation stopped: "stop", "length", "tool_calls", "content_filter", "function_call". OpenRouter may also return "error".
logprobs	object | null	Log probability information, if requested.

Response Message

Field	Type	Description
role	"assistant"	Always "assistant".
content	string | null	The message content.
refusal	string | null	Refusal message, if applicable.
annotations	array[Annotation] | null	URL citations (e.g. from web search).
audio	object | null	Audio response data.
tool_calls	array[ToolCall] | null	Tool calls generated by the model.

ToolCall

Field	Type	Description
id	string	The tool call ID.
type	"function"	Always "function".
function.name	string	Name of the called function.
function.arguments	string	JSON-encoded arguments.

CompletionUsage

Field	Type	Description
prompt_tokens	integer	Tokens in the prompt.
completion_tokens	integer	Tokens in the completion.
total_tokens	integer	Total tokens used.

Headers

See Custom Headers for the full list. Summary:

Header	Direction	Description
Authorization	Request	Bearer <sequrity-api-key>
X-Api-Key	Request	LLM provider API key (BYOK).
X-Features	Request	Security features (agent arch, classifiers, blockers).
X-Policy	Request	Security policy (SQRT rules).
X-Config	Request	Fine-grained config (FSM, prompts, response format).
X-Session-ID	Request	Explicit session ID for multi-turn conversations.
X-Session-ID	Response	Session ID assigned by the server.

Examples

Request

Single LLMDual LLM

SEQURITY_API_KEY="${SEQURITY_API_KEY:-your-sequrity-api-key}"
OPENROUTER_API_KEY="${OPENROUTER_API_KEY:-your-openrouter-key}"
SERVICE_PROVIDER="openrouter"
REST_API_URL="https://api.sequrity.ai/control/chat/${SERVICE_PROVIDER}/v1/chat/completions"

curl -X POST $REST_API_URL \
  -H "Authorization: Bearer $SEQURITY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: $OPENROUTER_API_KEY" \
  -H 'X-Features: {"agent_arch":"single-llm"}' \
  -d '{
    "model": "openai/gpt-5-mini",
    "messages": [{"role": "user", "content": "What is the largest prime number below 100?"}]
  }'

SEQURITY_API_KEY="${SEQURITY_API_KEY:-your-sequrity-api-key}"
OPENROUTER_API_KEY="${OPENROUTER_API_KEY:-your-openrouter-key}"
SERVICE_PROVIDER="openrouter"
REST_API_URL="https://api.sequrity.ai/control/chat/${SERVICE_PROVIDER}/v1/chat/completions"

curl -X POST $REST_API_URL \
  -H "Authorization: Bearer $SEQURITY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-Api-Key: $OPENROUTER_API_KEY" \
  -H 'X-Features: {"agent_arch":"dual-llm"}' \
  -d '{
    "model": "openai/gpt-5-mini",
    "messages": [{"role": "user", "content": "What is the largest prime number below 100?"}]
  }'

Response

Single LLMDual LLM

{
    "id": "gen-1769519573-03eFDboLr45TxWIgz76t",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "97\n\nExplanation: 99, 98, and 100 are composite ...",
                "role": "assistant"
            }
        }
    ],
    "created": 1769519573,
    "model": "openai/gpt-5-mini",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 186,
        "prompt_tokens": 16,
        "total_tokens": 202
    }
}

{
    "id": "e71f5e2f-fb81-11f0-a50b-b80bf871da67",
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "{\"status\": \"success\", \"final_return_value\": {\"value\": 97, \"meta\": {\"tags\": [], \"consumers\": [\"*\"], \"producers\": []}}}",
                "role": "assistant"
            }
        }
    ],
    "created": 1769519589,
    "model": "openai/gpt-5-mini,openai/gpt-5-mini",
    "object": "chat.completion",
    "usage": {
        "completion_tokens": 354,
        "prompt_tokens": 2885,
        "total_tokens": 3239
    }
}