xAI pricing for Amazon Bedrock
Standard on-demand prices in USD per 1 million tokens for 3 xAI models on Amazon Bedrock. Last updated Oct 19, 2026 from the AWS Price List API (versions published Oct 16, 2026 / Oct 12, 2026). Click a column to sort.
Sources: Amazon Bedrock pricing page · AWS Price List API
Pricing by provider
AI21 LabsAmazonAnthropicCohereDeepSeekGoogleMetaMiniMaxMistral AIMoonshot AINVIDIAOpenAIQwenWriterZ.AIxAI
FAQ
How is Amazon Bedrock pricing for xAI models calculated?
On-demand text models are billed per token, with separate prices for input and output tokens. The table shows standard on-demand USD prices per 1 million tokens. Batch, prompt caching, provisioned throughput, flex/priority and long-context rates are not included.
Does Bedrock pricing differ by AWS Region?
Sometimes. Many models have the same price everywhere they are offered, but some Regions or Global cross-Region inference profiles are priced differently. The Region notes column shows the reference Region used and the input price range across all priced Regions.
Which xAI model has the lowest input price?
In this data, Grok 4.3 lists the lowest input price at $1.25 per 1M input tokens (us-east-1 · Mantle In-Region). Cheapest is not always best: check context window, quality and retirement dates.
How often is this page updated?
ModelEOL rebuilds from the AWS Price List API every day. This version was built Oct 19, 2026.
ModelEOL is an independent project and is not affiliated with or endorsed by Amazon Web Services. Prices are copied from the public AWS Price List API; always confirm on the official Amazon Bedrock pricing page before you budget.