System One
Answer typed questions about a state with a decision model.
The System One API answers typed questions about a state in one request. Use it with a decision model. A decision model serves only POST /v1/systemone. It does not serve chat completions or text completions.
Endpoint
POST https://api.inference.net/v1/systemoneSend your API key in the Authorization: Bearer header, as for other endpoints. The response is one JSON object. The endpoint does not stream.
Request
| Field | Type | Required | Description |
|---|---|---|---|
model | string | Yes | The identifier of a decision model. |
state | string or object | Yes | The input the questions are about. |
questions | object | Yes | One or more questions, keyed by a question id that you choose. It must not be empty. |
Each value in questions is an object with these fields:
| Field | Type | Required | Description |
|---|---|---|---|
type | string | Yes | One of noul, choice or score. |
instructions | string | No | Instructions for this question. |
criteria | any | No | Criteria for this question. The API sends it to the model unchanged. |
The API sends other fields in the request body and in each question to the model unchanged.
curl https://api.inference.net/v1/systemone \
-H "Authorization: Bearer $INFERENCE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "<decision-model>",
"state": "The customer asks for a refund for an order that arrived damaged.",
"questions": {
"is_refund_request": { "type": "noul" },
"department": {
"type": "choice",
"instructions": "Pick the team that handles this ticket.",
"criteria": ["billing", "shipping", "support"]
}
}
}'Response
| Field | Type | Description |
|---|---|---|
model | string | The model identifier you sent. |
answers | object | One answer for each question, keyed by the question id from the request. The shape of each answer depends on the question type and the model. |
usage.input_tokens | integer | The number of input tokens the model read. |
usage.output_tokens | integer | The number of output tokens. A decision generates no tokens, so this is 0. |
{
"model": "<decision-model>",
"answers": {
"is_refund_request": { "...": "..." },
"department": { "...": "..." }
},
"usage": { "input_tokens": 41, "output_tokens": 0 }
}The x-inference-id response header contains the generation id.
Billing
You pay for usage.input_tokens as prompt tokens. There are no completion tokens.
Errors
Errors use the same JSON shape as other endpoints: {"error": {"message": "...", "type": "..."}}.
| Status | Cause |
|---|---|
| 400 | The body has no string model, no string or object state, or no non-empty questions object. |
| 400 | A question is not an object, or its type is not noul, choice or score. |
| 400 | The model is not a decision model. Call it with POST /v1/chat/completions or POST /v1/completions. |
| 400 | You called a decision model with POST /v1/chat/completions or POST /v1/completions. Call it with POST /v1/systemone. |
| 403 | Your team does not have access to the model. |
| 404 | The model does not exist. |