LLM Reference

Grok 2 Models by xAI

xAIGrok LicenseOpen weights
3 models2024Up to 128k ctxFrom $0.5/1M input

Details

ResearcherxAI
Commercial useCommercial use: conditional
Models3
Released2024
Max context128k

Capabilities

Multimodal1 of 3 models
Reasoning2 of 3 models
Structured Outputs1 of 3 models

About

Grok 2 is a family of 3 AI models by xAI, released in 2024.

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

3 in view

Use when the workload needs multimodal inputs.

2024-12multimodal inputs
Grok-2Current

Use when the workload needs 128k context, reasoning, and structured outputs.

2024-08128k contextreasoningstructured outputs

Use when the workload needs 128k context and reasoning.

2024-08128k contextreasoning

Release Timeline

2 release groups
2024-12
1 current
Grok 2 Vision
multimodal inputs
Current
2024-08
2 current
Grok-2
128k contextreasoningstructured outputs
Current
Grok-2 Mini
128k contextreasoning
Current

Specifications(3 models)

Grok 2 model specifications comparison
ModelReleasedContextMultimodalReasoningStructured Outputs
Grok 2 Vision2024-12YesNoNo
Grok-22024-08128kNoYesYes
Grok-2 Mini2024-08128kNoYesNo

Available From(1 provider)

Pricing

Grok 2 model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Grok-2SiliconFlow$0.5$0.5Serverless

Popular comparisons in this family

Frequently Asked Questions

What is Grok 2 used for?
Grok 2 is used for vision and multimodal work, reasoning, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
How does Grok 2 compare to Grok 1?
Grok 2 by xAI is strongest where you need vision and multimodal work, while Grok 1 by xAI is the closest related family to check for reasoning. Grok 2 has 3 listed variants and reaches up to 128k context, so compare the specs and pricing tables before choosing a production model.
Which Grok 2 model should I use?
For the lowest listed input price, start with Grok-2 through SiliconFlow at $0.5/1M input tokens. For the most capable/latest local choice, evaluate Grok-2 with 128k context and reasoning and structured outputs.