jishie

Kimi K3

perplexity-agent/moonshot-ai/kimi-k3 · family kimi-k3 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideo.

$6.00Blended $/1M (3:1)
$3Input $/1M
$15Output $/1M
$18.001M in + 1M out
$0.3 −90%Cache read $/1M
Cheapest rank
Provider
Perplexity Agent (perplexity-agent)
Context
1,048,576 tokens
Max output
131,072 tokens
Capabilities
toolsreasoningtextimagevideo

Same model, other providers

“Kimi K3” is offered by 9 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Kenarifreefree$0.001049k
Umans AI Coding Planfreefree$0.001049k
Kimi For Codingfreefree$0.001049k
Tinfoil$2$6$3.00256k
CrofAI$2$8$3.501000k
Requesty$2.25$11.25$4.501049k
NanoGPT$2.5$13.5$5.251049k
ai&$3$12.5$5.381049k
Perplexity Agent (this)$3$15$6.001049k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Perplexity Agent and pass this model id:

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

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