jishie

Kimi K3

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

$4.20
Blended $/1M (3:1)
$2.1
Input $/1M
$10.5
Output $/1M
$12.60
1M in + 1M out
$0.3 −86%
Cache read $/1M
#6933 of 8,509
Cheapest rank
Provider
ainetcafe (ainetcafe)
Kind
text (outputs text)
Context
262,144 tokens
Max output
32,768 tokens
Capabilities
tools reasoning text image

Same model, other providers

“Kimi K3” is offered by 79 providers — cheapest-effective first. Volcengine Ark Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Volcengine Ark Coding Planfreefree$0.001M
Nvidiafreefree$0.001M
Kimi For Coding (kimi.com)freefree$0.001M
Kimi For Coding (kimi.ai)freefree$0.001M
Umans AI Coding Planfreefree$0.001M
SenseNova (China)freefree$0.001M
SCNet Token Planfreefree$0.001M
NanoGPT$0.1495$7.15$1.901M
Kenari$0.8571$8.57$2.791M
OpenRouter$0.192$15$3.891M
engy$1.95$9.75$3.901.1M
ainetcafe (this)$2.1$10.5$4.20262k
Boundless$2.3$11.4$4.581M

Call it

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

Most providers are OpenAI-compatible — point base_url at ainetcafe 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 ainetcafe models · model index · JSON