---
title: "Kimi K3 (256K) — API access"
description: "Kimi K3 with a 256K window: official $3.00/$15.00 per 1M tokens, $1.50/$7.50 with the flat 50% apiToken.sale discount. Same model and same rates as k3, smaller accepted context."
url: "https://apitoken.sale/models/kimi-k3-256k"
language: "en"
---
# Kimi K3 (256K)

The same Kimi K3 at the same rates, with a 256K accepted window — for harnesses that expect a smaller context than the 1M variant.

- **Model ID:** `k3-256k`
- **Tier:** K3
- **Context window:** 256K tokens
- **Max output:** not published
- **Official price (per 1M):** $3 input / $15 output
- **Your price (per 1M):** input $1.5, output $7.5 (flat 50% off)
- **Base URL:** `https://router.apitoken.sale` · **Endpoint:** `POST /v1beta/models/k3-256k:generateContent` (x-goog-api-key)

## Best for

- Tools that cap or mis-handle a 1M-token window.
- Sessions where a smaller window keeps compaction predictable.

## Notes

- Cached input bills at 10% of input — caching is automatic on repeated prefixes.
- KIMI publishes no separate cache-write rate: a write is a cache miss and bills at the input rate.

## Call it

```bash
curl https://router.apitoken.sale/v1beta/models/k3-256k:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Reply with exactly: connected"}]}]}'
```

## FAQ

**Does k3-256k cost less than k3?**

No. It is the same model on the same rate card — $3.00/$15.00 officially, $1.50/$7.50 here. Only the accepted context differs.

**When should I pick it over k3?**

When your client compacts against the window it is told about: a harness configured for 256K will behave more predictably on this id than on the 1M one.

---
API reference: https://apitoken.sale/md/docs · All models: https://apitoken.sale/md/models