Vertex AI (OpenAI-compatible) Provider

Access partner models (e.g. xAI Grok) via Google Cloud Vertex AI's OpenAI-compatible Chat Completions endpoint.

Available Models

Grok 4.20 Reasoning

xai
grok-4-20-reasoning
Streaming
Vision
Tools
Reasoning
JSON Output
Vertex AI (OpenAI-compatible)
Context: 2M
Input
$2
/M tokens
Cached
$0.2
/M tokens
Output
$6
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤200K tokens
$2
$0.2
$6
>200K tokens
$4
$0.4
$12

Grok 4.20 Non-Reasoning

xai
grok-4-20-non-reasoning
Streaming
Vision
Tools
JSON Output
Vertex AI (OpenAI-compatible)
Context: 2M
Input
$2
/M tokens
Cached
$0.2
/M tokens
Output
$6
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤200K tokens
$2
$0.2
$6
>200K tokens
$4
$0.4
$12