jishie

Grok 4.20 (Non-Reasoning)

llmgateway/grok-4-20-non-reasoning · family grok · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools text image pdf.

$1.56
Blended $/1M (3:1)
$1.25
Input $/1M
$2.5
Output $/1M
$3.75
1M in + 1M out
$0.2 −84%
Cache read $/1M
#4754 of 7,708
Cheapest rank
Provider
DevPass (LLM Gateway) (llmgateway)
Kind
text (outputs text)
Context
2,000,000 tokens
Max output
30,000 tokens
Capabilities
tools text image pdf

Same model, other providers

“Grok 4.20 (Non-Reasoning)” is offered by 8 providers — cheapest-effective first. This one (DevPass (LLM Gateway)) is the cheapest.

ProviderInputOutputBlendedContext
DevPass (LLM Gateway) (this)$1.25$2.5$1.562M
Impossibl$1.25$2.5$1.561M
OCI Generative AI$1.25$2.5$1.561M
xAI$1.25$2.5$1.561M
Eden AI$1.25$2.5$1.561M
Vertex$1.25$2.5$1.562M
Azure$2$6$3.00262k
Cloudflare AI Gateway$2$6$3.002M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at DevPass (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-4-20-non-reasoning","messages":[{"role":"user","content":"hello"}]}'

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

← all DevPass (LLM Gateway) models · model index · JSON