{T}
TokenMath.net
Verified against xAI Official API Pricing
xAIflagshipGenerally AvailableCurrent Flagship

Grok 4.6 Token Counter & Cost Calculator

xAI flagship frontier model with 500k context, real-time reasoning, and prompt caching

Standard Input / 1M
$2.00
Prompt tokens
Cached Input / 1M
$0.50
Prompt caching rate
Output / 1M
$6.00
Generation completion
Context Window
500k
Max out: 128k
Official Provider Pricing ModesDocumented Schedules
Standard API
$2.00 in / $6.00 out
Cache: $0.50/1M
Batch API (-50%)
$1.00 in / $3.00 out
Cache: $0.25/1M
API & Developer Integration Details
generally available
API Model Stringgrok-4.6
Provider & FamilyxAI (cl100k_base)
Prompt Caching Rules1,024 min tokens (75% off)
Long-Context TiersStandard flat rate throughout full window
First-party audit timestamp: 2026-09-15 17:30 UTCOfficial Documentation

Interactive Cost & Token Simulator for Grok 4.6

Live Calculation
Input Tokens2,500
Output Tokens800
Requests / Day5,000
Prompt Caching Ratio (50%)$0.5/M cached rate
Cost / Request$0.00793
Daily Spend (5,000 reqs)$39.625
Monthly Run-Rate (30d)$1,188.75

Standard Workload Cost Scenarios

ScenarioInput TokensOutput TokensUncached CostWith Prompt Caching
Short Chat Query1,000500$0.00500$0.00350
Document Summarization10,0002,000$0.0320$0.0170
Codebase & Context Analysis100,00020,000$0.3200$0.1700
Batch Corpus Processing1,000,000100,000$2.60$1.10
Technical Architecture & Pricing VerificationVerified: 2026-09-15 17:30 UTC
Model ArchitectureGrok 4.6
Provider OrganizationxAI
Tokenizer EncodingxAI Byte-level BPE (~131k vocabulary)
API ConnectivityxAI Chat Completions API (/v1/chat/completions) with 500k context and prompt caching.
Batch API 50% DiscountSupported (50% off input & output)
0
Tier 1 Rate Quota60 RPM · 200k TPM
Blended 3:1 Cost / 1M Tokens$3.00
Standard billing rates: .00/1M input, .50/1M cached input (75% cache discount), .00/1M output. Tiered pricing applies above 200,000 context tokens. Batch processing receives 50% discount.xAI Official API Pricing

Verified Pricing History

September 2026: $2/M input · $6/M output ($0.5/M cached)
xAI Grok 4.6 flagship release with 500k context and prefix caching.

When to Choose Grok 4.6

Ideal for production workloads demanding flagship capabilities, deep context depth (500k tokens), and reliability from xAI. Excellent when predictable tokenomics and prompt caching support are paramount.

When Another Model May Be Better

If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.

Frequently Asked Questions About Grok 4.6

How much does 1 million tokens cost with Grok 4.6?

For Grok 4.6, 1 million input tokens costs $2.00, while 1 million output tokens costs $6.00. If using prompt caching, repetitive input prefixes are discounted to $0.50 per million.

What is the context window for Grok 4.6?

Grok 4.6 features a maximum context window of 500,000 tokens (~375,000 words), with a maximum output limit of 131,072 tokens per completion.

Which tokenizer does Grok 4.6 use?

Grok 4.6 utilizes the xAI Byte-level BPE (~131k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.

Does Grok 4.6 support prompt caching discounts?

Yes. Grok 4.6 supports prompt caching with a cached input rate of $0.50/1M (saving up to 75% on repeated input context).