Start building
xAI logoxAI / Model Developer

xAI AI Models
on SandBase

Grok language models and Grok Imagine visual generation.
Choose the xAI model capability that fits your next task.

LanguageImage & VideoAudio
Browse xAI Models ↓Get SandBase API Key ↗xAI AI ↗
20model & capability records
4 / 5 / 10 / 1language · image · video · audio
4 Sync16 async records

Catalog snapshot · Oct 10, 2026 · Task variants, not independent foundation models.

START WITH THE TASK

Choose a xAI Model

Balanced Agent WorkxAI: Grok 4.7 ↗$2000000/M inputHigh-Volume Text on a BudgetxAI: Grok 4.6 ↗$2000000/M inputAdvanced ReasoningxAI: Grok 4.5 ↗$2000000/M inputImage Generation & EditingGrok Imagine Image 2.0 Text to Image ↗From $0.06/requestCinematic VideoGrok Imagine Image 2.0 Edit ↗From $0.06/requestSpeech & MusicGrok Imagine Video 1.5 Text to Video ↗From $0.84/request

Recommendations are task-oriented starting points, not performance rankings. Confirm live pricing and schema.

EXPLORE THE CATALOG

xAI Models & Capabilities

Model IDs, task variants, and pricing units.
All in one place.

20 model & capability recordsCatalog snapshot · Oct 10, 2026

Token prices are per million input/output tokens; request prices are base prices. Context is shown only when meaningful. Confirm pricing, availability, and request fields on the live model page.

XAI / LLM4 records

Gemini

Language, multimodal understanding, reasoning, and tool use.

✓ Availablesync

xAI: Grok 4.7

x-ai/grok-4.7
chatvisionreasoningstructured outputfunction calling

500,000 context tokens

$2.00 / $6.00 per 1M tokens
✓ Availablesync

xAI: Grok 4.6

x-ai/grok-4.6
chatvisionreasoningstructured outputfunction calling

500,000 context tokens

$2.00 / $6.00 per 1M tokens
✓ Availablesync

xAI: Grok 4.5

x-ai/grok-4.5
chatvisionreasoningstructured outputfunction calling

500,000 context tokens

$2.00 / $6.00 per 1M tokens
✓ Availablesync

xAI: Grok 4.3

x-ai/grok-4.3
chatvisionreasoningstructured outputfunction calling

1,000,000 context tokens

$1.25 / $2.50 per 1M tokens
XAI / IMAGE5 records

Nano Banana

Generate images and edit visual inputs.

XAI / VIDEO10 records

Veo and Gemini Omni

Create, extend, edit, and transform video from text, images, and references.

XAI / AUDIO1 records

Audio (Gemini TTS and Lyria)

Turn text into speech and generate music.

MODELS ARE A CHOICE, NOT A LOCK-IN

Use xAI Models in an Agent Workflow

01Task→
02Model (Swappable)→
03Skills / Tools / APIs→
04Result→

Keep your model selection separate from the Agent. Check tool support and schema compatibility when swapping models.

YOUR CAPABILITIES. YOUR WORKFLOW.

One Key. More Ways to Build.

Get SandBase API Key　→