Chat Completions | SingularityAPI

POST /v1/chat/completions speaks the OpenAI chat completions wire format. Authenticate with Authorization: Bearer sapi_.... For everything not called out below — message formats, tool calling, response shape — see OpenAI Compatibility; this page only covers what’s specific to SingularityAPI.

Request notes

model — required. A catalog slug (e.g. deepseek-v4-flash) or contract/{slug} for a contract. Must match exactly; see Models & Pricing for the catalog.
Output limit field — max_tokens and max_completion_tokens are interchangeable; either caps output tokens on any chat model. Sending both in one request is a 400. The value must be a positive integer, no larger than the model’s max output. Omit it and the per-model default is injected server-side — check the receipt’s transformed_fields to see when the default (or a spelling rewrite) was applied.
stream — boolean. See Streaming for the SSE details.
Unsupported or reserved parameters are rejected with a 400, not silently dropped.

Function tools on gpt-5.6 models: always set reasoning_effort explicitly. On gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna, sending tools while omitting reasoning_effort fails with a 400 from the upstream provider (“Function tools with reasoning_effort are not supported … set reasoning_effort to ‘none’”). Include any explicit value — "none", "low", "medium", or "high" — and the same request succeeds: the platform automatically serves tools-plus-reasoning requests through the provider’s tools-compatible path. If your client treats a “none” setting by dropping the field, send the literal string "none" instead. Failed requests are never charged.

Example

curl https://api.singularityapi.dev/v1/chat/completions \
  -H "Authorization: Bearer $SINGULARITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Say hello."}]
  }'

A response looks like this:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1690000000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 10,
    "total_tokens": 19
  }
}

model in the response is the served model — the catalog model that actually ran the request. On a direct catalog call this matches what you sent; on a contract call it’s the contract’s current target.

Response headers

Every response carries:

x-singularity-request-id
x-singularity-receipt-id
x-singularity-contract-revision — present on contract calls only

Use the receipt ID to pull the exact cost and token usage from GET /v1/receipts/{id}.

Limits

A request may run up to ~230 seconds. Exceeding it returns 504 request_timeout.
Request bodies over the size cap are rejected with 413 request_too_large.

See Errors & Rate Limits for the full error envelope and status table.