Moonshot AI (Kimi)

Kimi K2.6

The Kimi K2.6 generation, a large open-weight MoE with thinking, available across inference gateways.

ActiveAvailable from 26 providers
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.

Source: Moonshot AI pricing, Kimi models

Price per 1M tokens
$1.2 in / $4.5 out
Context window262,144
Max output32,768
Cache read$0.2 / M
ModalitiesText → Text
Priced across26 providers

Pricing

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

Billing legRate
Input$1.2 / M
Output$4.5 / M
Cache read$0.2 / 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
$510
at current list prices
Fresh input$240
Cached input$0.00
Output incl. thinking$270
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
Together AI
$1.2$4.5$0.2—Direct
DigitalOceanLowest
$0.76$3.2$0.19—via OpenRouter
Inceptron
$0.65$3.41$0.14—via OpenRouter
Decart
$0.66$3.41$0.144—via OpenRouter
Modelrun
$0.7$3.4$0.15—via OpenRouter
Baidu
$0.684$3.42$0.144—via OpenRouter
Chutes
$0.66$3.5$0.33—via OpenRouter
SiliconFlow
$0.77$3.4$0.14—via OpenRouter
Novita
$0.8$3.4$0.16—via OpenRouter
DeepInfra
$0.75$3.5$0.15—via OpenRouter
Parasail
$0.75$3.5$0.16—via OpenRouter
Venice
$0.75$3.5$0.16—via OpenRouter
StreamLake
$0.855$3.6$0.144—via OpenRouter
Azure AI Foundry
$0.95$4$0.16—Direct
Fireworks AI
$0.95$4$0.16✓Direct
AtlasCloud
$0.95$4$0.16—via OpenRouter
Baseten
$0.95$4$0.16—via OpenRouter
Cloudflare
$0.95$4$0.16—via OpenRouter
Fireworks AI
$0.95$4$0.16—via OpenRouter
Moonshot-ai
$0.95$4$0.16—via OpenRouter
Nebius
$0.95$4——via OpenRouter
Wandb
$0.95$4$0.16—via OpenRouter
Azure AI Foundry (Fireworks)
$1.05$4.4$0.176—Direct
Phala
$1.09$4.6$0.37—via OpenRouter
Together AI
$1.2$4.5$0.2—via OpenRouter
Azure AI Foundry · Data zone
$1.05$5——Direct

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $1.2 / $4.5 per 1M since May 21, 2026.

More from Moonshot AI (Kimi)

Other models from the same provider.

Kimi K2.7 Code
moonshot/kimi-k2.7-code
$0.72 / $3.5 in / out per 1M
Kimi K2.5
moonshot/kimi-k2.5
$0.375 / $2.03 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 K2.6 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.