Moonshot model
Kimi K3 API cost calculator
Kimi K3 costs $3 per 1M input tokens and $15 per 1M output tokens on the Moonshot API, with a 1.0M-token context window. A typical request (2K input, 500 output tokens) costs $0.01 — about $405/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Kimi K3
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.0060 | $6.00 |
| RAG query with context | 4,000 / 500 | $0.02 | $19.50 |
| Document summarization | 20,000 / 1,000 | $0.07 | $75.00 |
| Agent coding session | 100,000 / 5,000 | $0.38 | $375 |
Kimi K3 vs other Moonshot models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Kimi K3 | $3 | $15 | 1.0M |
| Kimi K2.7 Code | $0.67 | $3.40 | 262K |
| Kimi K2.6 | $0.58 | $2.44 | 262K |
| Kimi K2.5 | $0.45 | $2.25 | 262K |
| Kimi K2 Thinking | $0.60 | $2.50 | 262K |
Frequently asked questions
How much does Kimi K3 cost per 1M tokens?
According to current pricing data, Kimi K3 costs $3 per 1M input tokens and $15 per 1M output tokens. Processing 1M tokens each way costs $18.00.
What does a typical API request to Kimi K3 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.01. At 1,000 requests per day that is $13.50 daily, or about $405 per month.
What is Kimi K3's context window?
Kimi K3 supports a 1.0M-token context window (1,048,576 tokens).
Does Kimi K3 support prompt caching?
Yes. Cached input tokens cost $0.30 per 1M — a 90% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Kimi K3?
Ling-2.6-flash from Inclusionai is currently the cheapest comparable option at $0.01 per 1M input tokens versus $3 for Kimi K3 — roughly 300x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Kimi K3 vs Ling-2.6-flash pricing, or run Kimi K3 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.