jishie

Kimi K2.7 Code Highspeed

empiriolabs/kimi-k2-7-code-highspeed · family kimi-k2 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideo.

$3.42Blended $/1M (3:1)
$1.9Input $/1M
$8Output $/1M
$9.901M in + 1M out
$1.9Cache read $/1M
#4417 of 5,000Cheapest rank
Provider
EmpirioLabs AI (empiriolabs)
Context
256,000 tokens
Max output
131,072 tokens
Capabilities
toolsreasoningtextimagevideo

Same model, other providers

“Kimi K2.7 Code Highspeed” is offered by 8 providers — cheapest-effective first. AIHubMix is the cheapest at $3.42 blended.

ProviderInputOutputBlendedContext
AIHubMix$1.9$7.999$3.42262k
EmpirioLabs AI (this)$1.9$8$3.42256k
LLM Gateway$1.9$8$3.42262k
Moonshot AI (China)$1.9$8$3.42262k
Ofox$1.9$8$3.42262k
GMI Cloud$1.9$8$3.42262k
Merge Gateway$1.9$8$3.42262k
Moonshot AI$1.9$8$3.42262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at EmpirioLabs 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-k2-7-code-highspeed","messages":[{"role":"user","content":"hello"}]}'

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