Grok 3 Fast
Pricing & Specs

xAI · $5 input / $25 output per 1M tokens · 131.072K context window

No longer offered on OpenMark

$5
per 1M input tokens
$25
per 1M output tokens
131.072K
context window (tokens)

Grok 3 Fast is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference — if you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Grok 3 Fast API Pricing

TokensPrice
Input$5 / 1M tokens
Output$25 / 1M tokens
Cached input$1.25 / 1M tokens

Cached tokens pricing is available for this model.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0175
1K 1,000 runs of that task: $17.50
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

Grok 3 Fast Specs

SpecValue
Context window131.072K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~544ms median response
Reasoning modelNo
Tool / function callingYes
JSON modeYes
StreamingYes
Prompt cachingYes

Capabilities

text generation reasoning function calling structured outputs streaming live search

Notes

Removed from xAI docs Jan 2026. Use grok-4-fast-reasoning instead.

FAQ

How much does Grok 3 Fast cost?

Grok 3 Fast costs $5 per 1M input tokens and $25 per 1M output tokens ($1.25 per 1M cached input tokens).

What is Grok 3 Fast's context window?

Grok 3 Fast has a 131.072K-token context window.

Can I test Grok 3 Fast on my own task?

Grok 3 Fast is no longer offered on OpenMark, but you can benchmark its current alternatives from xAI and other providers on your own task — free tier available.

Still using Grok 3 Fast?

It's been superseded. Benchmark its current alternatives on your actual
workload — you'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives — Free →