Skip to main content
Run inference with Fastino models through one of two API contracts. Each contract has its own request and response shape, and their fields are not interchangeable.

Make a decision with GLiDE

Call POST /v1/systemone with state and typed questions. Receive Noul, Choice, or Score answers with probabilities and confidence.

Run GLiNER

Call POST /v1/chat/completions with messages. Add a schema for GLiNER extraction, classification, structures, or relations.
For GLiDE concepts and primitive selection, start with Decision Models. The GLiDE inference guide covers the HTTP integration.

​
API contracts

GLiDE / System One

Complete request and response schema for decision-model inference.

GLiNER / Chat Completions

Complete OpenAI-compatible GLiNER contract.

Native GLiNER

Synchronous, asynchronous, and job-status contracts.

Responses

OpenAI Responses-compatible inference contract.

Messages

Anthropic Messages-compatible inference contract.

Models

List compatibility model IDs.

​
Confirm routing and retention

Successful calls to POST /v1/systemone, /v1/chat/completions, /v1/responses, /v1/messages, and /v1/gliner-2 return two diagnostic headers:
  • X-Fastino-Data-Retention is zero for team Zero Data Retention, not-stored when the request opted out of inference history, or stored otherwise.
  • X-Fastino-Served-Model is the canonical model that handled the call. It is the fine-tuned model ID when a fine-tune served the request and the base-model ID otherwise.
Inspect them when verifying an integration:
The headers are absent on error responses and streams that fail before provider dispatch. A stream that fails after dispatch retains them and reports its error in-band.

​
Cold starts and retries

An idle or newly deployed model may cold-start. Use a read timeout of at least 300 seconds and bounded backoff for 425, 429, and 503 responses. Respect Retry-After when present. A timed-out request can still warm the deployment, allowing the next request to succeed. Do not retry authentication, billing, validation, or unknown-model errors without correcting the underlying problem.