Grok 2 Vision is xAI's language model with a 33K context window, available from 2 providers, starting at $2.00 / 1M input and $10.00 / 1M output. A multimodal variant of Grok 2 from xAI that adds image understanding capabilities to the flagship LLM.
Specifications
Canonical IDxai-grok-2-vision
TypeLanguage
StatusDeprecated
CreatorxAIxAI
Providers
Context Window33K tokens
Input ModalitiesImage
Output ModalitiesText
Deprecation Date

Capabilities

Input1/5
Text·
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Image In
$ / 1M
Vercel AI Gateway logo
Vercel AI Gateway
vercel_ai_gateway/xai/grok-2-vision
$2.00$10.00N/A
xAI logo
xAI
xai/grok-2-vision
$2.00$10.00$2.00

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Grok 4.31.0M$1.25$2.50Available
Grok 4.202.0M$1.25$2.50Available
Grok 4.20 Multi-Agent2.0M$1.25$2.50Available
Grok 4.20 Multi-Agent Beta2.0M$1.25$2.50Available
Grok 4.20 Non-Reasoning2.0M$1.25$2.50Available
Grok 4.20 Reasoning2.0M$1.25$2.50Available
Grok 4.1 Fast2.0M$1.25$2.50Deprecated
Grok 4 Fast131K$0.200$0.500Deprecated
Grok 4 Fast Non-Reasoning2.0M$0.200$0.500Deprecated
Grok 4256K$1.25$2.50Deprecated
Grok 2 Vision33K$2.00$10.00Current

Model IDs

vercel_ai_gateway/xai/grok-2-vision
xai-grok-2-vision
xai/grok-2-vision
xai/grok-2-vision-1212
xai/grok-2-vision-latest