Moonshot AI (Kimi) API pricing
Updated
Moonshot AI (Kimi) lists standard per-token prices for 4 models. The cheapest is Kimi K2.6 at USD 0.95 input and USD 4 output per 1M tokens; the dearest is Kimi K3 at USD 3 / USD 15. It publishes cached-input prices for all of them, plus batch and fast tiers (no flex or priority). Checked 2026-11-14.
- Models with a standard price
- 4
- Median input / output
- USD 1.475 / USD 7
- Cached-input prices
- 4 of 4
- Cheapest host for
- 0 of 4 shared models
Which models is Moonshot AI (Kimi) the cheapest provider for?
None. Every one of the 4 models that Moonshot AI (Kimi) shares with other providers is cheaper elsewhere at the standard tier. The closest is Kimi K3.1 Pro, where Moonshot AI (Kimi) ranks 3 of 13. It is the dearest provider for 2.
How does Moonshot AI (Kimi) price the most widely hosted models?
The 4 models Moonshot AI (Kimi) sells that the most other providers also sell, with Moonshot AI (Kimi)'s rank among them on the 3:1 blend.
| Model | Moonshot AI (Kimi) | Rank | Cheapest |
|---|---|---|---|
| Kimi K3 | USD 3 / USD 15 | 5 of 18 | Chutes USD 1.85 / USD 9.50 |
| Kimi K3.1 Pro | USD 2 / USD 10 | 3 of 13 | DeepInfra USD 1.90 / USD 9.50 |
| Kimi K2.6 | USD 0.95 / USD 4 | 9 of 13 | Chutes USD 0.39 / USD 1.80 |
| Kimi K2.7 Code | USD 0.95 / USD 4 | 7 of 12 | CoreWeave Forge USD 0.60 / USD 3 |
Moonshot AI (Kimi) price list
USD per 1M tokens: 10 prices for 4 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means Moonshot AI (Kimi) is cheaper. Moonshot AI (Kimi) is the maker of every model here, so there is no maker price to compare with.
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
|---|---|---|---|---|---|---|---|
| Kimi K2.6 | standard batch | USD 0.95 USD 0.57 | USD 0.16 USD 0.10 | USD 4 USD 2.40 | 262,144 | own model | source source 2 |
| Kimi K2.7 Code | standard batch fast | USD 0.95 USD 0.57 USD 1.90 | USD 0.19 USD 0.114 USD 0.38 | USD 4 USD 2.40 USD 8 | 262,144 | own model | source source 2 |
| Kimi K3 | standard batch | USD 3 USD 1.80 | USD 0.30 USD 0.18 | USD 15 USD 9 | 1,048,576 | own model | source source 2 |
| Kimi K3.1 Pro | standard batch fast | USD 2 USD 1.20 USD 4 | USD 0.20 USD 0.12 USD 0.20 | USD 10 USD 6 USD 20 | 1,048,576 | own model | source source 2 |
- Cached "—" means Moonshot AI (Kimi)'s page shows no cache price for that row; budget cached tokens at the input price.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What service tiers does Moonshot AI (Kimi) publish?
- batch (4 rows). Across 4 models with both prices, the median batch price is 40% below standard. Moonshot AI (Kimi) row note: “Batch API, billed at 60% of the standard price. Cache writes are billed separately (5m and 1h TTL).”
- fast (2 rows). Across 2 models with both prices, the median fast price is 2× standard. Moonshot AI (Kimi) row note: “Highspeed variant, API model kimi-k3.1-pro-highspeed. Cache writes are billed separately (5m and 1h TTL).”
Cached input: 4 of 4 standard prices include a cache-read price, a median 13% of the input price. What cached input means.
What we recorded about Moonshot AI (Kimi)'s pricing page: Kimi Open Platform (platform.kimi.ai), international. Context windows from the page: K3 series 1,048,576 tokens, K2 series 262,144 tokens. Highspeed variants are listed as tier "fast". Batch prices from the BatchJob Pricing page.
BroadNet Inference and Moonshot AI (Kimi)
BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models Moonshot AI (Kimi) prices. BroadNet Inference pricing.
More on Moonshot AI (Kimi)
- Moonshot AI (Kimi)'s own pricing page (the source; checked 2026-11-14)
- All 41 providers compared · Cheapest LLM APIs right now · Download every price (CSV, JSON)
Questions
How much does the Moonshot AI (Kimi) API cost per token?
Moonshot AI (Kimi)'s standard prices run from USD 0.95 input and USD 4 output per 1M tokens (Kimi K2.6) to USD 3 / USD 15 (Kimi K3). The median across 4 standard prices is USD 1.475 input and USD 7 output per 1M, which is USD 0.000001475 per input token. Input, cached input and output are billed separately.
What is the cheapest model on Moonshot AI (Kimi)?
Kimi K2.6, at USD 0.95 input and USD 4 output per 1M tokens (USD 1.712 on a 3:1 input-to-output blend).
Is Moonshot AI (Kimi) cheaper than other providers?
It depends on the model. Of 4 models that other providers also price, Moonshot AI (Kimi) is the cheapest standard price for none; another provider is cheaper for 4; and it is the dearest for 2. Its median rank is 6 of a median 13 providers, on a 3:1 input-to-output blend.
Does Moonshot AI (Kimi) have batch, cached or priority pricing?
Cached input: yes, for 4 of 4 standard prices, at a median 13% of the input price. Other tiers: batch on 4 rows (median input 40% below standard); fast on 2 rows (median input 2× standard).
How much does a chatbot cost per month on Moonshot AI (Kimi)?
For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 114.84 on Kimi K2.6, USD 116.46 on Kimi K2.7 Code (the middle of Moonshot AI (Kimi)'s list) and USD 394.20 on Kimi K3. Try your own numbers.