Kimi K2 Instruct

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

$1.00Blended $/1M (3:1)

$0.57Input $/1M

$2.3Output $/1M

$2.871M in + 1M out

—Cache read $/1M

#3196 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 131,072 tokens
Max output: 131,072 tokens
Capabilities: toolstext

Same model, other providers

“Kimi K2 Instruct” is offered by 5 providers — cheapest-effective first. NanoGPT is the cheapest at $0.75 blended.

Provider	Input	Output	Blended	Context
NanoGPT	$0.4	$1.8	$0.75	256k
IO.NET	$0.39	$1.9	$0.77	33k
Vercel AI Gateway (this)	$0.57	$2.3	$1.00	131k
NovitaAI	$0.57	$2.3	$1.00	131k
Jiekou.AI	$0.57	$2.3	$1.00	131k

Call it

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

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