jishie

Kimi K3

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

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
Cache read $/1M
#214 of 6,789
Cheapest rank
Provider
Nvidia (nvidia)
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 55 providers — cheapest-effective first. This one (Nvidia) is the cheapest.

ProviderInputOutputBlendedContext
Nvidia (this)freefree$0.001M
Umans AI Coding Planfreefree$0.001M
Kenarifreefree$0.001M
SCNet Token Planfreefree$0.001M
Kimi For Codingfreefree$0.001M
CrofAI$2$8$3.501M
Requesty$2.03$10.13$4.051M
NanoGPT$2.5$13.5$5.251M
ai&$3$12.5$5.381M
Deep Infra$2.85$14.25$5.701M
DigitalOcean$2.85$14.25$5.701M
Cortecs$3$15$6.001M
Neuralwatt$3$15$6.001M

Call it

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

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