modelbenchmark.io

Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))

xAI · grok-4-20-non-reasoning

Compare

O-series reasoning model for hard analysis, math, coding, and planning

Specification

xai listing

Context
1M
Max output
1M
Released
2026-03-09
Knowledge cutoff
2025-09
Retires
2027-04-06
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · xai list price

Input
$1.25
Output
$2.50
Cache read
$0.20

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
200KCache read$0.40
200KInput$2.50
200KOutput$5.00

Available from 9 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
xaivendor$1.25$2.50$0.201M1M
azure_ai$1.25$2.50$1.25262K8K2027-04-06
google-vertex$1.25$2.50$0.202M30K
llmgateway$1.25$2.50$0.202M30K
llmgateway-providers · vertex-openai$1.25$2.50$0.202M30K
perplexity$1.25$2.50$0.20
vercel · spacexai$1.25$2.50
$0.20
$0.40
2M2M
vertex_ai$1.25$2.50$0.202M2M
azure$2.00$6.00262K8K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02vercel · spacexaiCache read$0.40
2026-09-04vercel · spacexaiCache read$0.20
2026-09-02vertex_aiInput$2.00
2026-09-11vertex_aiInput$1.25
2026-09-02vertex_aiOutput$6.00
2026-09-11vertex_aiOutput$2.50

More from xAI

most-hosted first