Moonshot AI (Kimi)

Kimi K3

Moonshot's July 2026 frontier Kimi K3: a 2.8T-parameter MoE with native vision, a 1M-token context window, and always-on max reasoning.

ActiveReleased July 16, 2026
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Moonshot AI pricing, Kimi models

Price per 1M tokens via Moonshot AI (OpenRouter)
$3 in / $15 out
Context window1,048,576
Max output1,048,576
Cache read$0.3 / M
ModalitiesText, Image → Text

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$3 / M
Output$15 / M
Cache read$0.3 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$1.5K
at current list prices
Fresh input$600
Cached input$0.00
Output incl. thinking$900
Track this automatically →

Provider

Where this model runs, and what it charges.

PlatformInput / MOutput / MCache read / MBatchAccess
Moonshot AI
$3$15$0.3—via OpenRouter

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $3 / $15 per 1M since July 19, 2026.

More from Moonshot AI (Kimi)

Other models from the same provider.

Kimi K2.7 Code
moonshot/kimi-k2.7-code
$0.85 / $3.8 in / out per 1M
Kimi K2.6
moonshot/kimi-k2.6
$1.2 / $4.5 in / out per 1M
Kimi K2.5
moonshot/kimi-k2.5
$0.57 / $2.85 in / out per 1M
Kimi K2 Thinking
moonshot/kimi-k2-thinking
$0.6 / $2.5 in / out per 1M
Kimi K2
moonshot/kimi-k2
$0.57 / $2.3 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Kimi K3 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.