jishie

Kimi K2 Turbo

moonshotai/kimi-k2-turbo-preview · family kimi-k2 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$4.30Blended $/1M (3:1)
$2.4Input $/1M
$10Output $/1M
$12.401M in + 1M out
$0.6 −75%Cache read $/1M
#4699 of 5,000Cheapest rank
Provider
Moonshot AI (moonshotai)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
toolstext

Same model, other providers

“Kimi K2 Turbo” is offered by 2 providers — cheapest-effective first. This one (Moonshot AI) is the cheapest.

ProviderInputOutputBlendedContext
Moonshot AI (this)$2.4$10$4.30262k
Moonshot AI (China)$2.4$10$4.30262k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"kimi-k2-turbo-preview","messages":[{"role":"user","content":"hello"}]}'

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