---
title: "The best API for chatbots and support"
canonical: "https://router.xark.io/use-cases/chatbots-and-support"
description: "Costing a production chat or support assistant, including the conversation-history growth that makes chat bills grow faster than traffic."
section: "use-cases"
updated: "2026-09-02"
source: "https://router.xark.io/use-cases/chatbots-and-support.md"
---

# The best API for chatbots and support

Chat costs grow faster than traffic, because each turn resends the whole conversation so far. A 20-turn conversation sends roughly ten times the tokens of a 2-turn one for the same number of replies — which is why per-conversation cost, not per-message cost, is the number worth modelling.

**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.

## Why this workload is different

Every turn resends the history. Costs scale with the square of conversation length, not linearly with messages, and a support bot that averages 12 turns costs far more than one averaging 4 even at identical volume.

The two effective levers are cached input on the fixed system prompt and a summarisation or truncation policy on older turns. Choosing a marginally cheaper model is usually a smaller win than capping how much history each turn carries.

## What actually matters when choosing

| Criterion | Why it decides this workload |
| --- | --- |
| Cached-input rate | The system prompt and persona are identical on every turn of every conversation — the clearest cache win of any workload. |
| Output rate | Unlike agents, chat produces substantial output. Here the output rate genuinely matters. |
| Latency | A human is waiting. Time to first token is felt directly, in a way it is not for a background job. |

## Recommended models, priced at 50,000 conversations/month, ~8 turns each

| Model | Our monthly cost | Official monthly cost | Saving | Callable | Document |
| --- | --- | --- | --- | --- | --- |
| DeepSeek V4 Flash | $61.20 | $95.20 | 36% | Yes | [read](https://router.xark.io/models/deepseek-v4-flash.md) |
| GLM-5.2 | $594.00 | $1,016.00 | 42% | Yes | [read](https://router.xark.io/models/glm-5-2.md) |
| Kimi K2.6 | $422.00 | $730.00 | 42% | Yes | [read](https://router.xark.io/models/kimi-k2-6.md) |

## Questions

### Does truncating history hurt quality?

Less than most teams expect for support workloads, where the useful context is usually the last few turns plus a summary. It is worth measuring on your own transcripts, because the cost difference is large and the quality difference often is not.