Kimi K2.6 pricing.
prices as of · 82 providers · 99 prices
Moonshot AI's Kimi K2.6 holds 262k tokens of context, reads images as well as text and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.
Kimi K2.6 costs $0.95 in and $4 out per million tokens from Moonshot AI; the cheapest price we can explain is $2.10 at Vultr Serverless Inference, checked 16 Sept 2026.
Moonshot AI list price
$6.85/M tokens
$0.95 in · $4 out
read · 93% above the market median
Cheapest price we can explain
$2.10/M tokens
$0.30 in · $1.20 out · 69% under list
Vultr Serverless Inferenceread
What it costs for your work
Moonshot AI list price
$0.81a month
cheapest we can explain · Vultr Serverless Inference
$0.252a month
difference
$0.558saved
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Every provider selling Kimi K2.6
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against Moonshot AI's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
Moonshot AIThe price Moonshot AI charges for the model it trained. Every row below is measured against it.
$0.95 / $4in / out per M
1.00×of list price
Cheaper, and we know why
38 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- Vultr Serverless Inference
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.30 / $1.20in / out per M
0.31×of list price
CrofHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.50 / $1.99in / out per M
0.51×of list price
- Crof
Serves the open weights at int4, a lower precision than the maker's, so not quite the same product.
int4 precisionCrof ↗$0.50 / $1.99in / out per M
0.51×of list price
NanoGPTRoutes to a host serving the open weights; precision not disclosed.
256k context hereNanoGPT ↗$0.50 / $2.60in / out per M
0.60×of list price
DecartServes the open weights at fp4, a lower precision than the maker's, so not quite the same product.
fp4 precisionDecart ↗$0.59 / $2.47in / out per M
0.62×of list price
StreamLakeServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
256k context herefp8 precision$0.60 / $2.52in / out per M
0.63×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
$0.52 / $2.87in / out per M
0.64×of list price
$0.60 / $3.05in / out per M
0.71×of list price
ChutesHosts the open weights on its own servers, so the price is its own, not a resale. Precision tee.
$0.58 / $3.40in / out per M
0.75×of list price
- Chutes
Serves the open weights at int4, a lower precision than the maker's, so not quite the same product.
int4 precisionChutes ↗$0.58 / $3.40in / out per M
0.75×of list price
Weights & BiasesHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.65 / $3.41in / out per M
0.78×of list price
CoreWeaveServes the open weights at fp4, a lower precision than the maker's, so not quite the same product.
fp4 precision$0.65 / $3.41in / out per M
0.78×of list price
$0.61 / $3.59in / out per M
0.79×of list price
LilacHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.70 / $3.50in / out per M
0.82×of list price
CrusoeHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.70 / $3.50in / out per M
0.82×of list price
- Crusoe
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision bf16.
bf16 precisionCrusoe ↗$0.70 / $3.50in / out per M
0.82×of list price
SiliconFlowServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
fp8 precisionSiliconFlow ↗$0.77 / $3.40in / out per M
0.83×of list price
$0.75 / $3.50in / out per M
0.84×of list price
VeniceHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
256k context hereVenice ↗$0.75 / $3.50in / out per M
0.84×of list price
$0.75 / $3.50in / out per M
0.84×of list price
DeepInfraHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.75 / $3.50in / out per M
0.84×of list price
- DeepInfra
Serves the open weights at fp4, a lower precision than the maker's, so not quite the same product.
fp4 precisionDeepInfra ↗$0.75 / $3.50in / out per M
0.84×of list price
- Venice
Serves the open weights at int4, a lower precision than the maker's, so not quite the same product.
$0.75 / $3.50in / out per M
0.84×of list price
ParasailServes the open weights at int4, a lower precision than the maker's, so not quite the same product.
int4 precisionParasail ↗$0.75 / $3.50in / out per M
0.84×of list price
NovitaHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.80 / $3.40in / out per M
0.85×of list price
showing the 25 cheapest of 38 · every row in the open dataset
Same price as the maker
50 pricesThe same price the maker charges, sold by someone else.
EBCloudThe same price Moonshot AI charges.
$0.93 / $3.86in / out per M
0.97×of list price
$0.93 / $3.86in / out per M
0.97×of list price
$0.95 / $4in / out per M
1.00×of list price
TokenGoThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
AurikoThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
- Ollama Cloud
The same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
- Clarifai
The same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
AIHubMixThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
OrcaRouterThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
Azure Cognitive ServicesThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
Hugging Face Inference ProvidersThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
FrogBotThe same price Moonshot AI charges.
256k context here$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
Merge GatewayThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
AbacusThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
OpenCode ZenThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
ClinePassThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
$0.95 / $4in / out per M
1.00×of list price
302.AIThe same price Moonshot AI charges.
$0.95 / $4in / out per M
1.00×of list price
showing the 25 cheapest of 50 · every row in the open dataset
Cheaper, and nobody says why
6 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
InceptronWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.52 / $2.87in / out per M
0.64×of list price
- Inceptron
We could not read this provider's prices reliably, so the row is listed but never ranked.
int4 precision$0.52 / $2.87in / out per M
0.64×of list price
$0.75 / $3.50in / out per M
0.84×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.80 / $3.40in / out per M
0.85×of list price
AmbientWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.95 / $4in / out per M
1.00×of list price
KenariWe could not read this provider's prices reliably, so the row is listed but never ranked.
$1 / $5in / out per M
1.17×of list price
Given away with limits
4 free tiers · never rankedThese providers give Kimi K2.6 away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
Alibaba Token Plan
NVIDIA build- SCNet Token Plan
Alibaba Token Plan (China)
Frequently asked
- Who sells Kimi K2.6 cheapest?
- Vultr Serverless Inference, at $0.30 in and $1.20 out per million tokens, read on 16 Sept 2026. Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
- Is Kimi K2.6 open weights?
- Yes. Moonshot AI publishes the weights, so anyone may host Kimi K2.6, which is why 82 providers sell it and why their prices differ so much.
- How much context does Kimi K2.6 hold?
- 262,144 tokens in one call, which is about 262k, and it can call your own functions.
- How does Kimi K2.6 compare with the rest of the market?
- At $6.85 per million tokens, Moonshot AI's price is 93% above the $3.55 median across the 337 text models we track.