jishie

Kimi K3 Fast

neuralwatt/kimi-k3-fast · family kimi-k3 · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.

$6.00
Blended $/1M (3:1)
$3
Input $/1M
$15
Output $/1M
$18.00
1M in + 1M out
$0.3 −90%
Cache read $/1M
#6861 of 7,708
Cheapest rank
Provider
Neuralwatt (neuralwatt)
Kind
text (outputs text)
Context
1,048,560 tokens
Max output
1,048,560 tokens
Capabilities
tools text image

Same model, other providers

“Kimi K3 Fast” is offered by 4 providers — cheapest-effective first. This one (Neuralwatt) is the cheapest.

ProviderInputOutputBlendedContext
Neuralwatt (this)$3$15$6.001M
Venice AI$4.5$22.5$9.001M
Vercel AI Gateway$4.5$22.5$9.001M
Fireworks AI$4.5$22.5$9.001M

Call it

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

Most providers are OpenAI-compatible — point base_url at Neuralwatt and pass this model id:

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

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

← all Neuralwatt models · model index · JSON