Skip to main content

Glossary

Terms used in the API, Console, and documentation.

Autoregressive model​

An LLM architecture that generates output one token at a time. Contrast with diffusion LLM.

Base URL​

The per-model API root: https://inference.cloud.celeris.ai/<model>/v1. The model is part of the path, ahead of the standard /v1 suffix — see Model routing.

celeris-1​

Celeris's diffusion language model for short, structured responses. See Models.

Chat completion​

The request/response shape of the primary endpoint, POST /chat/completions — a messages array in, a choices array out, in the standard OpenAI wire format.

Context window​

The hard ceiling on prompt plus completion tokens per request — 4,096 tokens for celeris-1. Oversized requests are rejected with a 400, never silently truncated. See Models.

Credit​

The prepaid unit of billing. Usage draws down the workspace's credit balance at per-token rates; an exhausted balance returns 402 until topped up.

Diffusion LLM​

A language model that refines multiple output tokens in parallel rather than generating them strictly one at a time. See Models.

Error envelope​

The JSON body returned for Celeris API errors: {"error": {message, type, code}}. Branch handling on the stable code field. See Errors.

Key (API key)​

The dg_-prefixed bearer credential sent as Authorization: Bearer dg_.... Created, revealed, rotated, and revoked in the Console. A key belongs to a workspace and is owned by either a user or the workspace itself. See Authentication.

Organization​

The unit of tenancy created when you sign up, containing one or more workspaces (starting with a Personal workspace). Teammates are invited at the organization level, as Developer or Admin. Workspace admins can view that workspace's billing details; organization Admins manage members, the saved billing method, and workspace admin actions. See Organizations and workspaces.

Playground​

The Console tool for testing prompts against the live model without writing client code. See Console.

Rate limit​

The per-workspace limit on sustained request rate. Exceeding it returns 429 with a Retry-After header. See Rate limits.

Region​

The cloud region that serves a request. Celeris is currently available in us-east-1 (N. Virginia). Network distance to the region affects end-to-end latency.

Retry-After​

The response header on every 429: the number of seconds to wait before retrying. Honor it as the floor under your backoff.

Server-Timing​

The response header on every successful request that reports combined server-side processing time. See Measuring latency.

service_busy​

One of the two 429 codes. It indicates temporary service capacity pressure; retry after Retry-After.

Commercial access​

Organization-level access requested from the Console. Requests activate when capacity is available; otherwise, they remain queued. Joining the queue does not charge the saved card. See Console § Commercial access.

Token​

The unit of model input/output and of billing. Every response's usage block reports prompt_tokens, completion_tokens, and total_tokens.

Trace ID (X-Client-Trace-Id)​

An optional caller-supplied request header that Celeris echoes in API responses. Use it to correlate application logs with support cases. See Support.

Usage​

The Console dashboard of completed request counts and token volumes over 24 hours, 7 days, or 30 days. Rejected requests are not included. See Console § Usage.

Workspace​

Where keys, credits, and usage live, inside an organization; signing up creates a Personal one, and you can create more and switch between them in the Console. A workspace must be activated (funded, or covered by a free starter credit) before it can create API keys. Credits and usage are shared across the workspace. API keys can be private to their owner or shared with the workspace. See Organizations and workspaces.