Kimi K3 API Pricing
Moonshot (Kimi) · context window 1M · prices updated 2026-10-30
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 12% and pricier than 88% of the models we track. It is the most expensive of the 9 Moonshot (Kimi) models we track. Output costs 78.1× more than input here, so anything that makes the model write less — tighter instructions, structured output, lower max_tokens — moves the bill more than trimming the prompt.
Cached input is 5% cheaper. On an input-heavy workload you need roughly a 100% 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. | $0.022 | $329 |
| Coding agent — 300 sessions/day (60K in / 12K out) Multi-step loops re-read the same files; caching matters more than raw price. | $0.1915 | $1724 |
| Long-context analysis — 200 runs/day (250K in / 4K out) Only possible on large-context models; input cost is nearly the whole bill. | $0.108 | $648 |
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 Oct 30, 2026 (+39% per output token), from $0.239/$10.80 to $0.192/$15.00 per 1M in/out. That is one of 30 repricings in the 89 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% |
| Sep 11, 2026 | $2.34 | $11.70 | -22% |
| Sep 12, 2026 | $2.30 | $11.55 | -1% |
| Sep 13, 2026 | $2.65 | $13.28 | +15% |
| Sep 17, 2026 | $3.00 | $15.00 | +13% |
| Sep 18, 2026 | $2.10 | $10.95 | -27% |
| Sep 19, 2026 | $1.70 | $8.50 | -22% |
| Sep 22, 2026 | $3.00 | $15.00 | +76% |
| Oct 1, 2026 | $0.6845 | $10.00 | -33% |
| Oct 2, 2026 | $2.70 | $13.50 | +35% |
| Oct 4, 2026 | $0.72 | $13.00 | -4% |
| Oct 5, 2026 | $0.67 | $14.00 | +8% |
| Oct 6, 2026 | $0.95 | $14.00 | 0% |
| Oct 7, 2026 | $0.62 | $15.00 | +7% |
| Oct 8, 2026 | $0.62 | $12.30 | -18% |
| Oct 9, 2026 | $0.5 | $12.00 | -2% |
| Oct 10, 2026 | $0.64 | $13.50 | +13% |
| Oct 11, 2026 | $0.8 | $10.00 | -26% |
| Oct 12, 2026 | $0.73 | $10.00 | 0% |
| Oct 14, 2026 | $0.7 | $15.00 | +50% |
| Oct 15, 2026 | $0.45 | $15.00 | 0% |
| Oct 16, 2026 | $0.304 | $11.94 | -20% |
| Oct 19, 2026 | $0.239 | $11.94 | 0% |
| Oct 24, 2026 | $0.239 | $10.80 | -10% |
| Oct 26, 2026 | $0.18 | $20.00 | +85% |
| Oct 27, 2026 | $0.2 | $20.00 | 0% |
| Oct 28, 2026 | $0.189 | $20.00 | 0% |
| Oct 29, 2026 | $0.239 | $10.80 | -46% |
| Oct 30, 2026 | $0.192 | $15.00 | +39% |
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 $2.81 more per million input tokens. 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 $0.192 per million input tokens and $15.00 per million output tokens, with cached input at $0.182 per million (5% 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 $0.022 per request and $329 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 $0.2013 at $0.192 per million tokens — before any output. With prompt caching that same fill drops to about $0.1908 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 (9 of 9 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.