SpaceXAI

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by SpaceXAI

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
Grok 4.20 x-ai/grok-4.20:xai	2M	$1.31/M	$2.63/M	$0.21/M	0.6s	90 tps
Grok 4.20 Multi-Agent x-ai/grok-4.20-multi-agent:xai	2M	$1.31/M	$2.63/M	$0.21/M	41.7s	219 tps
Grok 4.3 x-ai/grok-4.3:xai	1M	$1.31/M	$2.63/M	$0.21/M	0.5s	88 tps
Grok 4.5 x-ai/grok-4.5:xai	500k	$2.10/M	$6.30/M	$0.31/M	0.9s	53 tps
Grok 4.6 x-ai/grok-4.6:xai	500k	$2.10/M	$6.30/M	$0.53/M	1.3s	55 tps

Prices are per million tokens. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using SpaceXAI via the API

For models with provider selection, append :xai to the model ID, set "provider": "xai" in the request body, or send an X-Provider: xai header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.20:xai",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.