RentGPU RentGPU
Trouver un GPU →
by xAI

xAI: Grok 4.20.

multimodal closed 2M ctx
Cheapest input
$1.25/M
on xAI
Cheapest output
$2.5/M
on xAI
Fastest
55 tok/s
on OpenRouter
Hosted equiv.
~$0.9/hr
@ 100 tok/s on xAI

Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...

Hosted API only

No self-host path — closed weights.

xAI: Grok 4.20's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
xAI api direct $1.25 $2.5 Launch ↗
OpenRouter api aggregator $1.25 $2.5 Launch ↗
Performance

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 54.7 776 ms 1754 ms
FAQ

Frequently asked.

How do I run xAI: Grok 4.20?
xAI: Grok 4.20 is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access xAI: Grok 4.20?
xAI: Grok 4.20 is available via xAI, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run xAI: Grok 4.20?
API pricing starts at $1.25/M input tokens and $2.5/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is xAI: Grok 4.20 open-source or proprietary?
xAI: Grok 4.20 is a proprietary model from xAI. Access is API-only — there are no public weights to download.