jishie

Kimi K2.6

crusoe/moonshotai/Kimi-K2.6 · family kimi-k2 · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtextimagevideo.

$1.40Blended $/1M (3:1)
$0.7Input $/1M
$3.5Output $/1M
$4.201M in + 1M out
$0.35 −50%Cache read $/1M
#3524 of 5,861Cheapest rank
Provider
Crusoe (crusoe)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
toolsreasoningtextimagevideo

Same model, other providers

“Kimi K2.6” is offered by 58 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.00262k
Alibaba Token Planfreefree$0.00262k
Kenarifreefree$0.00262k
Alibaba Token Plan (China)freefree$0.00262k
LLM Gateway$0.22$1.14$0.45262k
routing.run$0.275$1.1$0.48200k
Vultr$0.3$1.2$0.52262k
CrofAI$0.5$1.99$0.87262k
NanoGPT$0.5$2.6$1.02256k
Inceptron$0.6$3.41$1.30262k
Neuralwatt$0.69$3.22$1.32262k
Weights & Biases$0.65$3.41$1.34262k
Crusoe (this)$0.7$3.5$1.40262k

Call it

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

Most providers are OpenAI-compatible — point base_url at Crusoe 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-K2.6","messages":[{"role":"user","content":"hello"}]}'

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