Grok 4.5

kenari/grok-4-5 · family grok · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

freeBlended $/1M (3:1)

freeInput $/1M

freeOutput $/1M

free1M in + 1M out

—Cache read $/1M

#141 of 5,000Cheapest rank

Provider: Kenari (kenari)
Context: 500,000 tokens
Max output: 500,000 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“Grok 4.5” is offered by 9 providers — cheapest-effective first. This one (Kenari) is the cheapest.

Provider	Input	Output	Blended	Context
Kenari (this)	free	free	$0.00	500k
Impossibl	$2	$6	$3.00	500k
CrossModel	$2	$6	$3.00	500k
OpenCode Go	$2	$6	$3.00	500k
NanoGPT	$2	$6	$3.00	500k
DaoXE	$2	$6	$3.00	500k
LLM Gateway	$2	$6	$3.00	500k
OpenCode Zen	$2	$6	$3.00	500k
GitHub Copilot	$2	$6	$3.00	500k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"grok-4-5","messages":[{"role":"user","content":"hello"}]}'

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