Grok 4.7

grok-4.7by xAI

Grok 4.7 for coding, agentic tasks, and knowledge work. Text and image input with reasoning, tool calls, and structured output.

Compare Open in Playground

Context

500K

Max output

450K

Pricing

$1.60/M in$0.40/M cached$4.80/M out

Waterfall

1xAI via Experiential Clouduses exp creditsgrok-4.7$2 /M in·$6 /M out97.3% up257 tok/s2.81s

Supported parameters

Sampling

Temperature0-2Top-p0-1Logprobs

Tools & structure

ToolsStructured output

Reasoning

											Status
Experiential Cloud	no data	no data	99.9%	500K	450K	$1.60$3.20 past 200K	$4.80$9.60 past 200K	cache$0.40$0.80 past 200K	-	no data	disabled	-
xAI via Experiential Cloudexperiential	257 tok/s	2.81s	97.3%	500K	450K	$2$4 past 200K	$6$12 past 200K	cache$0.50$1 past 200K	-	no data	active	measured

Quickstart

I want you to route my LLM calls for "grok-4.7" through the Experiential gateway instead of
calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL
and key swap. Please:

1. Point the client at https://api.experientiallabs.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If
   it isn't set, stop and tell me to create one under Settings -> API Keys and export it.
3. Use the model id "grok-4.7" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key,
   leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my
   Experiential credits.

Tell me which files you changed.

Set EXPLABS_API_KEY to an organization API key before running your agent.

Model

Release notes