Skip to content

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

Kimi K2.6Kimi K3

A month of tokens

  • Kimi K2.6$105.00
  • Kimi K3$355.00

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

Kimi K2.6Kimi K3
Input per 1M$0.57$1.4
Output per 1M$2.4$10.8
Cached input$0.114$0.3
Batch in / outn/an/a
Blended (3:1)$1.03$3.74
Context262K1M
Routes2120
ReleasedApr 20, 2026Jul 16, 2026
Leadersboard scoren/a11 (#18)

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

Kimi K2.6

Way to buyIn / out per 1M
DigitalOcean
Default region · cached $0.114
$0.57 / $2.4Same as list
Decart
fp4 · cached $0.099
$0.587 / $2.47+3% vs list
StreamLake
fp8 · cached $0.101
$0.599 / $2.52+5% vs list
Chutes
int4 · cached $0.05
$0.5 / $2.85+6% vs list
Inceptron
int4 · cached $0.128
$0.497 / $2.97+9% vs list
CoreWeave
fp4 · cached $0.15
$0.65 / $3.41+30% vs list
Crusoe
bf16 · cached $0.35
$0.7 / $3.5+36% vs list
SiliconFlow
fp8 · cached $0.14
$0.77 / $3.4+39% vs list
DeepInfra
fp4 · cached $0.15
$0.75 / $3.5+40% vs list
Parasail
int4 · cached $0.16
$0.75 / $3.5+40% vs list
Venice
int4 · cached $0.16
$0.75 / $3.5+40% vs list
Novita AI
Default region · cached $0.16
$0.8 / $3.4+41% vs list
GMICloud
fp8 · cached $0.144
$0.855 / $3.6+50% vs list
AtlasCloud
int4 · cached $0.16
$0.95 / $4+67% vs list
Baidu
fp4 · cached $0.16
$0.95 / $4+67% vs list
Baseten
fp4 · cached $0.16
$0.95 / $4+67% vs list
Cloudflare Workers AI
Default region · cached $0.16
$0.95 / $4+67% vs list
Fireworks AI
Default region · cached $0.16
$0.95 / $4+67% vs list
Moonshot AI
int4 · cached $0.16
$0.95 / $4+67% vs list
Sail Research
int4 · cached $0.2
$1 / $4+70% vs list
Phala
Default region · cached $0.37
$1.09 / $4.6+91% vs list

Kimi K3

Way to buyIn / out per 1M
InferenceNet
fp4 · cached $0.3
$1.4 / $10.8Same as list
Sail Research
fp4 · cached $0.3
$1.5 / $11.5+7% vs list
Phala
Default region · cached $0.21
$2.1 / $10.5+12% vs list
Relace
fp4 · cached $0.21
$2.1 / $10.5+12% vs list
Makora
Default region · cached $0.256
$2.55 / $12.8+36% vs list
Wafer
Default region · cached $0.199
$1.99 / $14.5+37% vs list
DigitalOcean
Default region · cached $0.255
$2.55 / $13+38% vs list
Morph
Default region · cached $0.29
$2.5 / $14+44% vs list
DeepInfra
bf16 · cached $0.285
$2.85 / $14.3+53% vs list
Baseten
fp8 · cached $0.3
$3 / $15+61% vs list
Chutes
mxfp4 · cached $0.3
$3 / $15+61% vs list
Fireworks AI
Default region · cached $0.3
$3 / $15+61% vs list
Modal
mxfp4 · cached $0.3
$3 / $15+61% vs list
Moonshot AI
mxfp4 · cached $0.3
$3 / $15+61% vs list
Parasail
fp4 · cached $0.3
$3 / $15+61% vs list
Together AI
Default region · cached $0.3
$3 / $15+61% vs list
Fireworks AI
us · cached $0.33
$3.3 / $16.5+77% vs list
Qwen (Alibaba)
Default region · cached $0.345
$3.45 / $17.3+85% vs list
Fireworks AI
fast · cached $0.45
$4.5 / $22.5+141% vs list
Morph
fast · cached $0.6
$6 / $22.5+171% vs list

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.