--- title: "LLM reranking and probability docs for the SDK and API" description: "Learn the decision primitives, integrate the SDK, or make your first API request." canonical: "https://system-one.dev/en/docs" language: "en" --- # LLM reranking and probability docs for the SDK and API Learn the decision primitives, integrate the SDK, or make your first API request. ## System One SDK Install the TypeScript SDK, connect a provider, and work with typed questions and answers. [Read SDK documentation](https://docs.system-one.dev/en/docs/sdk) ## System One API Your first HTTP request, authentication, models, limits, errors, and credit billing. [Read API documentation](https://docs.system-one.dev/en/docs/api) ## Connect the SDK to System One API Follow the hosted API connection guide to set your endpoint, platform key, and retry policy. [Connect SDK to hosted API](https://docs.system-one.dev/en/docs/getting-started) ## When to use System One Use System One to route a request among named choices, score a condition against an ordered rubric, or estimate P(true) before an application branches. Define the answer space first. Keep business actions in application code, and escalate uncertain decisions to a person or a reasoning model. Validate performance on representative inputs before relying on a threshold. ## Response metadata Read X-System-One-Credits for the current debit, X-Request-Id for platform tracking, X-Idempotency-Replayed for replay status and X-System-One-Response-Mode for the transport. Safe native provider JSON and extensions are preserved. Platform metadata is not inserted into the provider response body. ## Failure and retry accounting Credits are reserved before inference and returned on a recorded failed inference. A successful replay using the same Idempotency-Key and body incurs no new inference or debit while its replay record remains available. Different input with the same key is rejected. After a timeout or uncertain result, check recorded usage before retrying and preserve the key. Reconciliation can be pending; do not assume a refund until the recorded outcome confirms it. ## Request limits Text-only models allow up to 65536 request bytes. Image-capable Clef models allow up to 13MB; check GET /v1/models for the selected model’s current, possibly tighter limits. Maximum 32 questions, 255 choices, 10 score levels and nesting depth 32. Model listing is public and does not consume inference credits. ## Compare Clairic and decision models This list shows every decision model you can call on system-one.dev, including Clairic. Each page says what inputs it can read, how many questions you can ask at once, and how many credits a call costs. ### Jev Provided by: system-one.dev TypeSafe's decision model. It reads text and JSON and returns a choice, a score, or a yes/no answer. - Provided by: system-one.dev - 1 credit per question per 4KB - Up to 32 questions · 64KB per request - Inputs: text and JSON - Pick one: up to 255 options; Score: 2–10 levels - Released 2026-09-18 [Model page](https://system-one.dev/en/models/jev) ### Clef Flash Provided by: system-one.dev Structured classification and routing for high-volume, cost-sensitive work. - Provided by: system-one.dev - 3 credits per question per 4KB - Up to 32 questions · 13MB per request - Inputs: text, JSON, and images (PNG, JPEG, WebP) - Images: up to 4 · 4MB each · 8MB total - Pick one: up to 255 options; Score: 2–10 levels - Released 2026-10-01 [Model page](https://system-one.dev/en/models/clef-flash) ### Clef Provided by: system-one.dev The highest-priced of the three Clef models. It reads text, JSON, and images and returns a choice, a score, or a yes/no answer. - Provided by: system-one.dev - 6 credits per question per 4KB - Up to 32 questions · 13MB per request - Inputs: text, JSON, and images (PNG, JPEG, WebP) - Images: up to 4 · 4MB each · 8MB total - Pick one: up to 255 options; Score: 2–10 levels - Released 2026-10-01 [Model page](https://system-one.dev/en/models/clef) ### Clef Omni Provided by: system-one.dev A decision model that reads text and images and returns a choice, a score, or a yes/no answer. - Provided by: system-one.dev - 4 credits per question per 4KB - Up to 32 questions · 13MB per request - Inputs: text, JSON, and images (PNG, JPEG, WebP) - Images: up to 4 · 4MB each · 8MB total - Pick one: up to 255 options; Score: 2–10 levels - Released 2026-10-09 [Model page](https://system-one.dev/en/models/clef-omni) ### Decider Provided by: system-one.dev Reads text and JSON and returns a choice, a score, or a yes/no answer. - Provided by: system-one.dev - 1 credit per question per 4KB - Up to 32 questions · 64KB per request - Inputs: text and JSON - Pick one: up to 255 options; Score: 2–10 levels - Released 2026-10-07 [Model page](https://system-one.dev/en/models/decider-v1-1) ### Clairic Provided by: system-one.dev An extraction model that returns typed values from text, JSON and images. - Provided by: system-one.dev - 2 credits per 4KB of input - Inputs: text, JSON, and images (PNG, JPEG, WebP) - Images: up to 4 · 4MB each · 8MB total - Released 2026-10-19 [Model page](https://system-one.dev/en/models/clairic) Prices are in credits. Token usage is shown for reference only; you are charged by model, number of questions and 4KB blocks. ## Start here - [Developer documentation](https://docs.system-one.dev/en) - [Versioning and deprecation](https://docs.system-one.dev/en/docs/api/versioning) - [Idempotency and retries](https://docs.system-one.dev/en/docs/api/idempotency) - [API errors](https://docs.system-one.dev/en/docs/api/errors) - [TypeScript SDK](https://system-one.dev/en/sdk) - [API reference](https://system-one.dev/en/api) - [Models](https://system-one.dev/en/models) - [Model catalog](https://docs.system-one.dev/en/docs/models) - [Authentication](https://system-one.dev/en/auth.md) - [Pricing](https://system-one.dev/en/pricing) - [Credit billing](https://docs.system-one.dev/en/docs/billing) - [OpenAPI specification](https://system-one.dev/openapi.json) - [Agent integration guide](https://system-one.dev/en/skill.md) - [System One for Coding Agents: Cursor, Claude Code, Codex](https://docs.system-one.dev/en/docs/coding-agents) - [Installable coding-agent skill](https://system-one.dev/skills/system-one/SKILL.md) - [About](https://system-one.dev/en/about) - [Contact](https://system-one.dev/en/contact) - [Playground samples](https://system-one.dev/en/demo) - [Blog](https://system-one.dev/en/blog) - [SDK source](https://github.com/ziyu/system-one-sdk) - [@system-one-ai/core (npm)](https://www.npmjs.com/package/@system-one-ai/core)