jishie

Inkling

kilo/thinkingmachines/inkling · family ling · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimageaudio.

$1.72Blended $/1M (3:1)
$0.95Input $/1M
$4.05Output $/1M
$5.001M in + 1M out
$0.16 −83%Cache read $/1M
#3815 of 5,000Cheapest rank
Provider
Kilo Gateway (kilo)
Context
524,288 tokens
Max output
262,144 tokens
Capabilities
toolsreasoningtextimageaudio

Same model, other providers

“Inkling” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.001049k
Kilo Gateway (this)$0.95$4.05$1.72524k
OpenRouter$0.95$4.05$1.721049k
Deep Infra$0.95$4.05$1.72524k
Baseten$1$4.05$1.761049k
NanoGPT$1$4.05$1.761048k
Together AI$1$4.05$1.76524k
Merge Gateway$1$4.05$1.761048k
Vercel AI Gateway$1$4.05$1.76256k

Call it

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

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

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