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 name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
Grok 4.20 x-ai/grok-4.20:xai	2M	$1.31/M	$2.63/M	$0.21/M	2.1s	54 tps
Grok 4.20 Multi-Agent x-ai/grok-4.20-multi-agent:xai	2M	$1.31/M	$2.63/M	$0.21/M	29.5s	258.5 tps
Grok 4.3 x-ai/grok-4.3:xai	1M	$1.31/M	$2.63/M	$0.21/M	1.3s	82 tps
Grok 4.5 x-ai/grok-4.5:xai	500k	$2.10/M	$6.30/M	$0.31/M	1.9s	59 tps
Grok 4.6 x-ai/grok-4.6:xai	500k	$2.10/M	$6.30/M	$0.53/M	2.7s	50 tps
Grok 4.7 x-ai/grok-4.7:xai	500k	$2.10/M	$6.30/M	$0.53/M	2s	67 tps

Grok 4.20

x-ai/grok-4.20:xai

Context

2M

Input /M

$1.31/M

Output /M

$2.63/M

Cache read /M

$0.21/M

TTFT

2.1s

Throughput

54 tps

Grok 4.20 Multi-Agent

x-ai/grok-4.20-multi-agent:xai

Context

2M

Input /M

$1.31/M

Output /M

$2.63/M

Cache read /M

$0.21/M

TTFT

29.5s

Throughput

258.5 tps

Grok 4.3

x-ai/grok-4.3:xai

Context

1M

Input /M

$1.31/M

Output /M

$2.63/M

Cache read /M

$0.21/M

TTFT

1.3s

Throughput

82 tps

Grok 4.5

x-ai/grok-4.5:xai

Context

500k

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.31/M

TTFT

1.9s

Throughput

59 tps

Grok 4.6

x-ai/grok-4.6:xai

Context

500k

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.53/M

TTFT

2.7s

Throughput

50 tps

Grok 4.7

x-ai/grok-4.7:xai

Context

500k

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.53/M

TTFT

2s

Throughput

67 tps

Prices are per million tokens. TTFT is the observed time to first token. 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

Call a model served by SpaceXAI using its displayed model ID, including the provider suffix when selection is supported.

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"}]
  }'

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.

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