jishie

Kimi K3

watt/Kimi-K3 · family kimi-k3 · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$6.00
Blended $/1M (3:1)
$3
Input $/1M
$15
Output $/1M
$18.00
1M in + 1M out
—
Cache read $/1M
#8087 of 9,232
Cheapest rank
Provider
Watt Cloud (watt)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
1,048,576 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Kimi K3” is offered by 29 providers — cheapest-effective first. Kimi For Coding (kimi.com) is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kimi For Coding (kimi.com)freefree$0.001M
Nvidiafreefree$0.001M
SenseNova (China)freefree$0.001M
Umans AI Coding Planfreefree$0.001M
Volcengine Ark Coding Planfreefree$0.001M
Kimi For Coding (kimi.ai)freefree$0.001M
SCNet Token Planfreefree$0.001M
NanoGPT$0.45$9.6$2.741M
Kenari$0.8571$8.57$2.791M
KoRouter$1.74$8.7$3.481M
JZSTOKEN$1.95$9.73$3.901M
engy$1.95$9.75$3.901.1M
Watt Cloud (this)$3$15$6.001M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Watt Cloud and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"Kimi-K3","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Watt Cloud models · model index · JSON