Answer questions with System One

POST/v1/systemone

Answer questions with System One.

Compatible with TypeSafe System One's answer endpoint: send a state and named questions, get one typed answer per question. model, state and questions are required (400 without them). With a virtual key a provider/ prefix on model is removed before the call.

Authenticate with a TypeSafe virtual key or with x-provider: typesafe and x-api-key; any other provider is a 422, and a PLATFORM virtual key is a 400. The key's checks, the plan's limits and the organization's approved-provider policy (403) apply. INPUT guardrails (the key's and x-guardrail) run over every text in state and each question's instructions; a REDACT rewrites the text and a BLOCK is a 422. Usage is priced per token from TypeSafe's reported usage. Without x-retry-count a failed call is retried up to 3 times on 429 and 5xx (including TypeSafe's 529). TypeSafe's own errors are returned unchanged: status, body and Retry-After.

Authorization

AuthorizationBearer <slug>.<secret>
A virtual key's API key (vk-....<secret>), as Authorization: Bearer. What the OpenAI SDK sends from its api_key. Used by the inference endpoints.
orx-virtual-keyheader
A virtual key's API key in the x-virtual-key header, for clients that keep Authorization for something else.
orx-api-keyheader
Direct credentials: the provider's own API key in x-api-key, with the provider named in x-provider (for example openai). On /v1/messages a virtual key is accepted in x-api-key too, which is what the Claude SDK sends.

Headers

x-providerstring
With direct credentials: the provider x-api-key belongs to, for example openai or anthropic (case and dashes are normalised). Not used with a virtual key.
x-retry-countinteger<int32>
How many times to retry a failed provider call, 0 to 5. Without the header, chat completions, Claude Messages and prompt completions do not retry, and the other endpoints retry up to 3 times. Retries back off exponentially from 1 second and honour a numeric Retry-After. The number made is in the x-retry-count response header.
x-retry-status-codesstring
Comma-separated provider status codes to retry on. Default 429,500,502,503,504,529.
x-guardrailstring
A guardrail slug (gr-...) to apply to this request, in addition to any the virtual key carries. A BLOCK is a 422 with x-guardrail-status: BLOCK.

Request body application/json

the questions to answer, in TypeSafe's format

modelstringrequired
The System One model, for example jev-latest. With a virtual key a provider/ prefix is removed.
stateobjectrequired
What the questions are about: text or any JSON value.
questionsmap<string, object>required
The questions to answer, keyed by a name you choose. The response has one answer per name.

Responses

200application/json

modelstringrequired
The model that answered: the versioned model behind an alias such as jev-latest.
answersmap<string, object>required
One answer per question, keyed by the names used in questions.
usageobjectrequired
The tokens a System One request used.
Child attributes
- input_tokensinteger<int32>required
  Tokens read from the state and questions.
- output_tokensinteger<int32>required
  Tokens produced.

Request

curl -X POST "https://api.vectoraxis.ai/v1/systemone" \
  -H "Authorization: Bearer $VECTORAXIS_VIRTUAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "string",
  "state": {},
  "questions": {
    "key": {
      "type": "noul",
      "instructions": {}
    }
  }
}'

VectorAxis is built by GK Labs, a member of NVIDIA Inception.