Grok 4.20 Beta Reasoning

vercel/xai/grok-4.20-reasoning-beta · 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

$0.2 −84%Cache read $/1M

#3677 of 5,000Cheapest rank

Provider: Vercel AI Gateway (vercel)
Context: 2,000,000 tokens
Max output: 2,000,000 tokens
Capabilities: toolsreasoningtextimagepdf

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":"xai/grok-4.20-reasoning-beta","messages":[{"role":"user","content":"hello"}]}'

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