---
title: "Kimi K3 — API access"
description: "Kimi K3 API pricing: official $3.00/$15.00 per 1M tokens, $1.50/$7.50 with the flat 50% apiToken.sale discount. Moonshot's frontier model with a 1M-token window."
url: "https://apitoken.sale/models/kimi-k3"
language: "en"
---
# Kimi K3

Kimi K3 is Moonshot's frontier model — a 1M-token window for agentic coding and long-context work, addressed as k3 on the Anthropic Messages lane.

- **Model ID:** `k3`
- **Tier:** K3
- **Context window:** 1M 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:generateContent` (x-goog-api-key)

## Best for

- Agentic coding sessions that outgrow a 256K window.
- Long-context analysis across a whole repository or corpus.
- Work already configured for Claude Code, which selects this window as k3[1m].

## 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: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 the Kimi K3 API cost?**

Officially $3.00 per 1M input tokens and $15.00 per 1M output tokens, with cached input at $0.30. On apiToken.sale the same requests cost 50% less — $1.50/$7.50 at the flat discount applied to every call.

**What is the model ID for Kimi K3?**

k3, or kimi/k3 on the unified router. Claude Code users can also send k3[1m], which is that client's spelling for the same 1M window — both settle identically.

**Is there a 256K variant?**

Yes: k3-256k is the same model and the same rate card with a 256K accepted window. Choose it when a smaller window is what your harness expects.

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