Skip to content

Compare model prices

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

Kimi K2.7 CodeKimi K3

A month of tokens

  • Kimi K2.7 Code$131.25
  • Kimi K3$299.14

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

Side by side

Kimi K2.7 CodeKimi K3
Input per 1M$0.713$0.885
Output per 1M$3$10.5
Cached input$0.143$0.33
Batch in / outn/an/a
Blended (3:1)$1.28$3.3
Context262K1M
Routes1619
ReleasedJun 12, 2026Jul 16, 2026
Leadersboard scoren/a9 (#18)

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper

Every route

Kimi K2.7 Code

Way to buyIn / out per 1M
StreamLake
Default region · cached $0.143
$0.713 / $3Same as list
Inceptron
int4 · cached $0.18
$0.656 / $3.3+3% vs list
DeepInfra
fp4 · cached $0.136
$0.68 / $3.4+6% vs list
CoreWeave
int4 · cached $0.15
$0.71 / $3.5+10% vs list
Venice
int4 · cached $0.16
$0.75 / $3.5+12% vs list
ModelRun
fp4 · cached $0.16
$0.85 / $3.75+23% vs list
SiliconFlow
fp8 · cached $0.18
$0.859 / $3.8+24% vs list
Novita AI
int4 · cached $0.182
$0.912 / $3.84+28% vs list
Baseten
fp4 · cached $0.16
$0.95 / $4+33% vs list
Cloudflare Workers AI
Default region · cached $0.19
$0.95 / $4+33% vs list
Fireworks AI
Default region · cached $0.19
$0.95 / $4+33% vs list
GMICloud
fp8 · cached $0.19
$0.95 / $4+33% vs list
Moonshot AI
int4 · cached $0.19
$0.95 / $4+33% vs list
Nebius
fp4
$0.95 / $4+33% vs list
Qwen (Alibaba)
fp8 · cached $0.19
$0.95 / $4+33% vs list
Moonshot AI
highspeed, int4 · cached $0.38
$1.9 / $8+167% vs list

Kimi K3

Way to buyIn / out per 1M
Sail Research
fp4 · cached $0.33
$0.885 / $10.5Same as list
Morph
Default region · cached $0.189
$1.63 / $9.1+6% vs list
InferenceNet
fp4 · cached $0.3
$1.3 / $11.4+16% vs list
Phala
Default region · cached $0.21
$2.1 / $10.5+27% vs list
Relace
fp4 · cached $0.21
$2.1 / $10.5+27% vs list
Makora
Default region · cached $0.204
$2.04 / $12.8+43% vs list
DigitalOcean
Default region · cached $0.255
$2.55 / $13+56% vs list
Wafer
Default region · cached $0.3
$1.99 / $15+59% vs list
DeepInfra
bf16 · cached $0.285
$2.85 / $14.3+73% vs list
Baseten
fp8 · cached $0.3
$3 / $15+82% vs list
Chutes
mxfp4 · cached $0.3
$3 / $15+82% vs list
Fireworks AI
Default region · cached $0.3
$3 / $15+82% vs list
Modal
mxfp4 · cached $0.3
$3 / $15+82% vs list
Moonshot AI
mxfp4 · cached $0.3
$3 / $15+82% vs list
Parasail
fp4 · cached $0.3
$3 / $15+82% vs list
Together AI
Default region · cached $0.3
$3 / $15+82% vs list
Fireworks AI
us · cached $0.33
$3.3 / $16.5+100% vs list
Qwen (Alibaba)
Default region · cached $0.345
$3.45 / $17.3+109% vs list
Fireworks AI
fast · cached $0.45
$4.5 / $22.5+173% vs list

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.