Grok 4.20

venice/grok-4-20 · family grok · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.

$1.77Blended $/1M (3:1)

$1.42Input $/1M

$2.83Output $/1M

$4.251M in + 1M out

$0.23 −84%Cache read $/1M

#3837 of 5,000Cheapest rank

Provider: Venice AI (venice)
Context: 2,000,000 tokens
Max output: 128,000 tokens
Capabilities: toolsreasoningtextimage

Same model, other providers

“Grok 4.20” is offered by 4 providers — cheapest-effective first. Merge Gateway is the cheapest at $1.56 blended.

Provider	Input	Output	Blended	Context
Merge Gateway	$1.25	$2.5	$1.56	1000k
OpenRouter	$1.25	$2.5	$1.56	2000k
Venice AI (this)	$1.42	$2.83	$1.77	2000k
NanoGPT	$2	$6	$3.00	2000k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"grok-4-20","messages":[{"role":"user","content":"hello"}]}'

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