Grok 4.7

Same model, served by 3 providers.

xaiClosed500k contextReleased 2026-09-21xai/grok-4.7

Providers

Show flex / batch / priority tiers Full precision only

Provider	Their model id	Serving	Input	Output	Cached in	Blended 3:1	Source
Azure AI Foundry	`grok-4.7`	standardglobal endpointQuantization not disclosed	$2.0	$6.0	$0.50	$3.0	Provider API Verified 3h ago · Changed 6h ago More prices cache read (long context): $1.0 input (long context): $4.0 output (long context): $12.0
AWS Bedrock	`global.xai.grok-4.7`	standardQuantization not disclosed	$2.0	$6.0	$0.50	$3.0	Unverified (via models.dev) Verified 5h ago · Changed 5h ago
Google Vertex AI	`xai/grok-4.7`	standardQuantization not disclosed	$2.0	$6.0	$0.50	$3.0	Unverified (via models.dev) Verified 5h ago · Changed 5h ago More prices cache read (prompts > 200k): $1.0 input (prompts > 200k): $4.0 output (prompts > 200k): $12.0
Azure AI Foundry	`grok-4.7`	standarddata zone (US)Quantization not disclosed	$2.2	$6.6	$0.55	$3.3	Provider API Verified 3h ago · Changed 6h ago More prices cache read (long context): $1.1 input (long context): $4.4 output (long context): $13.2
AWS Bedrock	`us.xai.grok-4.7`	standardQuantization not disclosed	$2.2	$6.6	$0.55	$3.3	Unverified (via models.dev) Verified 5h ago · Changed 5h ago

Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.

Monthly cost estimate

Input tokens / month (M)Output tokens / month (M)Cache hit (% of input)% of requests over 200k tokens

Azure AI Foundry global endpoint	$320/mo
AWS Bedrock	$320/mo
Google Vertex AI	$320/mo
Azure AI Foundry data zone (US)	$352/mo
AWS Bedrock	$352/mo

Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.