xAI

The lab behind Grok — Elon Musk's AI company, now folded into SpaceX — serving the Grok frontier models from its Colossus supercluster.

Start building View requests Official status

Models on xAI

Open in catalog

12 of 12

Grok 4Chatgrok-4256K contextRouteprimary$1.25 / $2.50per M input / output

Grok 4.20Chatgrok-4.201M contextRouteprimary$1.25 / $2.50per M input / output

Grok 4.20 FastChatgrok-4.20-fast1M contextRouteprimary$1.25 / $2.50per M input / output

Grok 4.3Chatgrok-4.31M contextRouteprimary$1.25 / $2.50per M input / output

Grok 4.5Chatgrok-4.5500K contextRouteprimary$2.00 / $6.00per M input / output

Grok 4.6Chatgrok-4.6Released Aug 12, 2026500K contextRouteprimary$2.00 / $6.00per M input / output

Grok Build 0.1Chatgrok-build-0.1256K contextRouteprimary$1.00 / $2.00per M input / output

Grok ImagineImagegrok-imagineRouteprimary$0.02/image

Grok Imagine Image 2.0Imagegrok-imagine-image-2.0Routeprimary$0.04/image

Grok Imagine Image QualityImagegrok-imagine-image-qualityRouteprimary$0.05/image

Grok Imagine VideoVideogrok-imagine-videoRouteprimary$0.75/video

Grok Imagine Video 1.5Videogrok-imagine-video-1.5Routeprimary$1.2/video

Performance

Response latency estimates

Time to first token

Generation speed · tok/s

Request success

Text-model timing and speed, plus API request success. Daily latency percentiles are estimates.

Direct routingCall xAI explicitly

xai· routing

# pin every request to xAI
curl https://www.ninjachat.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "routing": { "providers": { "only": ["xai"] } }
  }'