Kimi K3 API Pricing
Moonshot (Kimi) · context window 1M · prices updated 2026-09-07
Where Kimi K3 sits on price
At $15.00 per million output tokens, Kimi K3 is a premium tier model — 6.8× the median output price of $2.20, which puts it cheaper than 14% and pricier than 86% of the models we track. It sits 7th cheapest of the 8 Moonshot (Kimi) models we track. Output costs 5.0× input, the usual spread — trim both, starting with the answer length.
Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Kimi K3
These three workloads are the ones teams actually run on a premium-priced model — a $15.00/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.036 | $540 |
| Coding agent — 300 sessions/day (60K in / 12K out) Multi-step loops re-read the same files; caching matters more than raw price. | $0.36 | $3240 |
| Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. | $0.81 | $4860 |
Model your exact traffic in the API cost calculator — it preloads Kimi K3 with caching and batch options.
Kimi K3 price history
Moonshot (Kimi) last raised Kimi K3's output price on Aug 29, 2026 (+18% per output token), from $2.55/$12.75 to $3.00/$15.00 per 1M in/out. That is one of 2 repricings in the 36 days we have tracked it — worth knowing before you hard-code today's rate into a budget.
| Date | Input /1M | Output /1M | Output change |
|---|---|---|---|
| Aug 2, 2026 (tracking began) | $3.00 | $15.00 | — |
| Aug 28, 2026 | $2.55 | $12.75 | -15% |
| Aug 29, 2026 | $3.00 | $15.00 | +18% |
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
Kimi K3 vs Claude Sonnet 4.6
The closest-priced alternative from another vendor is Claude Sonnet 4.6 (Anthropic) — priced within a rounding error on output, with identical input pricing. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See Claude Sonnet 4.6 pricing →Cheaper alternatives
More Moonshot (Kimi) models
Frequently asked questions
› How much does the Kimi K3 API cost?
Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens, with cached input at $0.3 per million (90% cheaper). That works out to roughly 66,667 output tokens per dollar.
› What does the support chatbot workload cost on Kimi K3?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.036 per request and $540 per month on Kimi K3. Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Kimi K3's 1M context window?
Sending 1M of input in a single request costs $3.15 at $3.00 per million tokens — before any output. With prompt caching that same fill drops to about $0.3146 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Kimi K3 worth the price?
Kimi K3 sits in the middle of the market (7 of 8 by price within Moonshot (Kimi)). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.