jishie

Kimi K3

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

$2.74
Blended $/1M (3:1)
$0.45
Input $/1M
$9.6
Output $/1M
$10.05
1M in + 1M out
$0.13 −71%
Cache read $/1M
#6036 of 8,511
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
1,048,576 tokens
Max output
943,718 tokens
Capabilities
tools reasoning text image video

Same model, other providers

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

ProviderInputOutputBlendedContext
Umans AI Coding Planfreefree$0.001M
Kimi For Coding (kimi.com)freefree$0.001M
SCNet Token Planfreefree$0.001M
Kimi For Coding (kimi.ai)freefree$0.001M
Volcengine Ark Coding Planfreefree$0.001M
Nvidiafreefree$0.001M
SenseNova (China)freefree$0.001M
NanoGPT (this)$0.45$9.6$2.741M
Kenari$0.8571$8.57$2.791M
engy$1.95$9.75$3.901.1M
OpenRouter$0.192$16$4.141M
ainetcafe$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 NanoGPT and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"moonshotai/kimi-k3","messages":[{"role":"user","content":"hello"}]}'

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

← all NanoGPT models · model index · JSON