jishie

Kimi K3

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

$12.00
Blended $/1M (3:1)
$6
Input $/1M
$30
Output $/1M
$36.00
1M in + 1M out
Cache read $/1M
#7057 of 7,381
Cheapest rank
Provider
Inco (inco)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
131,072 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Kimi K3” is offered by 68 providers — cheapest-effective first. SenseNova (China) is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
SenseNova (China)freefree$0.001M
Kenarifreefree$0.001M
Nvidiafreefree$0.001M
Umans AI Coding Planfreefree$0.001M
SCNet Token Planfreefree$0.001M
Volcengine Ark Coding Planfreefree$0.001M
Kimi For Codingfreefree$0.001M
CrofAI$2$8$3.501M
NanoGPT$2$10$4.001M
Vancine$2.4$12$4.801M
DigitalOcean$2.55$12.95$5.151M
ai&$3$12.5$5.381M
Inco (this)$6$30$12.001M

Call it

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

Most providers are OpenAI-compatible — point base_url at Inco 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:fast","messages":[{"role":"user","content":"hello"}]}'

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

← all Inco models · model index · JSON