LLMPrice.io

Grok 3 Mini Fast API pricing

Published on-demand rates for xAI's xai/grok-3-mini-fast, captured 2026-08-10 from public pricing data and committed to our archive. Context window 131k tokens; first observed in our archive 2025-06-16.

MeterUSD per 1M tokens
Input$0.600
Output$4.00
Cached input$0.150

Standard on-demand rates. Excludes batch endpoints and negotiated pricing; confirm on xAI's pricing page before committing.

What it costs on a real workload

The four frozen profiles the LLMPrice indices price, per 1M tokens processed, at the rates above. Where no cache-read rate is published, the whole input bills at the standard rate.

ProfileIn / out mixCached shareCost
Retrieval800k / 200k70%$1.03
Chat500k / 500k30%$2.23
Content200k / 800k20%$3.30
Agent900k / 100k85%$0.596

Profile definitions are frozen and published on the methodology page. Compare every model on these profiles →

Observed rate history

ObservedInputOutputCached input
2025-06-16$0.600$4.00entered our archive
2026-02-01$0.600$4.00$0.150repricing observed

Dates are when we observed the rate in our own snapshots, which can lag the provider's announcement. Rates per 1M tokens.

Priced near this one

The models closest to Grok 3 Mini Fast on a retrieval workload, cheaper and more expensive alike. We publish no quality score, so this is what they cost and nothing more.

ModelProviderInputOutputvs Grok 3 Mini Fast
SonarPerplexity$1.00$1.003% less
GPT 5.4 MiniOpenAI$0.750$4.509% more
Grok 4.3xAI$1.25$2.5011% less
Claude Haiku 4.5Anthropic$1.00$5.0026% more

Compared on the retrieval profile: 800k input, 200k output, 70% of input cached where the model offers a cache rate.

Price your own prompt on it Estimate a whole project Plain rate card xAI's console →

No affiliate or referral arrangements: the console link carries no parameters and nothing on this page is paid placement. Grok 3 Mini Fast is a trademark of its owner; LLMPrice.io is independent and unaffiliated.