---
title: "Kimi for Coding — API access"
description: "Kimi for Coding API pricing: official $0.95/$4.00 per 1M tokens, $0.48/$2.00 with the flat 50% apiToken.sale discount. Moonshot's coding SKU with a 256K window."
url: "https://apitoken.sale/models/kimi-for-coding"
language: "en"
---
# Kimi for Coding

Kimi for Coding is Moonshot's coding SKU — a stable alias that tracks the current coding model, at roughly a third of the K3 token price.

- **Model ID:** `kimi-for-coding`
- **Tier:** Coding
- **Context window:** 256K tokens
- **Max output:** not published
- **Official price (per 1M):** $0.95 input / $4 output
- **Your price (per 1M):** input $0.475, output $2 (flat 50% off)
- **Base URL:** `https://router.apitoken.sale` · **Endpoint:** `POST /v1beta/models/kimi-for-coding:generateContent` (x-goog-api-key)

## Best for

- High-volume coding work where K3 token prices dominate the bill.
- Setups that want a stable id rather than a pinned model version.

## 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/kimi-for-coding:generateContent \
  -H "x-goog-api-key: $APITOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"contents": [{"parts": [{"text": "Reply with exactly: connected"}]}]}'
```

## FAQ

**How much does Kimi for Coding cost?**

Officially $0.95 per 1M input tokens and $4.00 per 1M output tokens, with cached input at $0.19. On apiToken.sale that is $0.48/$2.00 at the flat 50% discount.

**Which model does it actually run?**

It is a stable alias maintained by Moonshot that resolves to the current coding model. Pinning a dated id instead is what causes silent retry loops in third-party tools.

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