LLM PricesModelsChangelog
Prices in USD per 1M tokens, text only. Each price shows where it came from and when it was last verified. Prices marked unverified come from models.dev (community-maintained) until we read them from the provider directly.
← All models

Grok 4.3

Same model, served by 3 providers.

xaiClosed1M contextReleased 2026-04-17xai/grok-4.3

Providers

Standard tier onlyFull precision only
ProviderTheir model idServingInputOutputCached inBlended 3:1Source
Azure AI Foundry
grok-4.3
standardglobal endpointQuantization not disclosed
$1.25$2.5$0.20$1.56
Provider API
Verified 4h ago · Changed 7h ago
More prices
  • cache read (long context): $0.40
  • input (long context): $2.5
  • output (long context): $5.0
AWS Bedrock
xai.grok-4.3
standardQuantization not disclosed
$1.25$2.5$0.20$1.56
Unverified (via models.dev)
Verified 6h ago · Changed 6h ago
Google Vertex AI
xai/grok-4.3
standardQuantization not disclosedReduced context (200k of 1M)
$1.25$2.5$0.20$1.56
Unverified (via models.dev)
Verified 6h ago · Changed 6h ago
More prices
  • cache read (prompts > 200k): $0.40
  • input (prompts > 200k): $2.5
  • output (prompts > 200k): $5.0
Azure AI Foundry
grok-4.3
standarddata zone (US)Quantization not disclosed
$1.38$2.75$0.22$1.72
Provider API
Verified 4h ago · Changed 7h ago
More prices
  • cache read (long context): $0.44
  • input (long context): $2.75
  • output (long context): $5.5

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

Azure AI Foundry global endpoint$175/mo
AWS Bedrock $175/mo
Google Vertex AI $175/mo
Azure AI Foundry data zone (US)$192.5/mo

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