Grok 4.3

llmgateway/grok-4-3 · family grok · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagepdf.

$1.56Blended $/1M (3:1)

$1.25Input $/1M

$2.5Output $/1M

$3.751M in + 1M out

$0.3125 −75%Cache read $/1M

#3651 of 5,000Cheapest rank

Provider: LLM Gateway (llmgateway)
Context: 1,000,000 tokens
Max output: 30,000 tokens
Capabilities: toolsreasoningtextimagepdf

Same model, other providers

“Grok 4.3” is offered by 9 providers — cheapest-effective first. This one (LLM Gateway) is the cheapest.

Provider	Input	Output	Blended	Context
LLM Gateway (this)	$1.25	$2.5	$1.56	1000k
Impossibl	$1.25	$2.5	$1.56	1000k
CrossModel	$1.25	$2.5	$1.56	1000k
NanoGPT	$1.25	$2.5	$1.56	1000k
FastRouter	$1.25	$2.5	$1.56	1000k
DaoXE	$1.25	$2.5	$1.56	1000k
FrogBot	$1.25	$2.5	$1.56	1000k
ZenMux	$1.25	$2.5	$1.56	1000k
Abacus	$1.25	$2.5	$1.56	1000k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"grok-4-3","messages":[{"role":"user","content":"hello"}]}'

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