---
title: "Which model fits which job"
canonical: "https://router.xark.io/use-cases"
description: "8 workloads, each with the models that suit it and a worked monthly cost at a stated volume."
section: "core"
updated: "2026-09-02"
source: "https://router.xark.io/use-cases.md"
---

# Which model fits which job

8 workloads, each with the models that suit it and a worked monthly cost at a stated volume.

**Availability:** 7 of the 24 catalogued models are callable today. The rest are listed at their intended rate but no configured upstream serves them, so a request naming one returns `no available channel`. Every table below marks which is which.

| Workload | Query it answers | Volume priced | Best saving | Document |
| --- | --- | --- | --- | --- |
| Coding agents | best api for coding agent | a working agent, ~2,000 steps/month | 42% | [read](https://router.xark.io/use-cases/coding-agents.md) |
| RAG and retrieval | cheapest embeddings api for rag | 100,000 queries/month, 4K context each | 42% | [read](https://router.xark.io/use-cases/rag-and-retrieval.md) |
| Chatbots and support | cheapest llm api for chatbot | 50,000 conversations/month, ~8 turns each | 42% | [read](https://router.xark.io/use-cases/chatbots-and-support.md) |
| Document summarisation | cheapest llm api for summarising documents | 20,000 documents/month, ~40K tokens each | 40% | [read](https://router.xark.io/use-cases/document-summarisation.md) |
| Structured data extraction | best llm api for json extraction from documents | 400,000 documents/month, ~3K tokens each | 42% | [read](https://router.xark.io/use-cases/structured-data-extraction.md) |
| Semantic search and embeddings | cheapest embedding api for semantic search | a 5M-chunk corpus re-indexed monthly, plus 2M searches | 40% | [read](https://router.xark.io/use-cases/semantic-search-and-embeddings.md) |
| Translation and localisation | cheapest llm api for translation at scale | a localisation pipeline, ~420M source tokens/month | 42% | [read](https://router.xark.io/use-cases/translation-and-localisation.md) |
| Content generation | cheapest llm api for generating long form content | 60,000 pieces/month, ~2,500 tokens each | 42% | [read](https://router.xark.io/use-cases/content-generation.md) |