jishie

Grok 4.20 (Non-Reasoning)

impossibl/xai/grok-4.20-0309-non-reasoning · family grok · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstextimagepdf.

$1.56Blended $/1M (3:1)
$1.25Input $/1M
$2.5Output $/1M
$3.751M in + 1M out
$0.2 −84%Cache read $/1M
#3645 of 5,000Cheapest rank
Provider
Impossibl (impossibl)
Context
1,000,000 tokens
Max output
30,000 tokens
Capabilities
toolstextimagepdf

Same model, other providers

“Grok 4.20 (Non-Reasoning)” is offered by 5 providers — cheapest-effective first. This one (Impossibl) is the cheapest.

ProviderInputOutputBlendedContext
Impossibl (this)$1.25$2.5$1.561000k
LLM Gateway$1.25$2.5$1.562000k
xAI$1.25$2.5$1.561000k
LLM Gateway$2$6$3.002000k
Azure$2$6$3.00262k

Call it

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

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"xai/grok-4.20-0309-non-reasoning","messages":[{"role":"user","content":"hello"}]}'

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