Grok 4.6 API Pricing

xAI · released Aug 12, 2026 · 500K context · API model ID grok-4.6

Grok 4.6 by xAI API pricing: $2.00 per 1M input tokens and $6.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).

Prices

Grok 4.6 prices, USD per 1M tokens
PriceUSD per 1M tokens
Input$2.00
Output$6.00
Cache read$0.50
Cache writeNot published

xAI's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation

Estimated monthly cost

$1,500

per month

per day
$50.00
per request
$0.005

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.

Compare this workload across models

Long-context prices

Prompts longer than the threshold are billed at a higher rate.

Prompts overInputOutputCache readCache write
200,000 tokens$4.00$12.00$1.00Not published

Monthly cost by workload

WorkloadPer month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day$1,500/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day$2,850/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input$1,560/mo

Context and capabilities

Context
500,000 tokens
Max output
500,000 tokens
Input
text, image, pdf
Output
text
Knowledge cutoff
Feb 1, 2026
Open weights
No
Tool calling
Yes
Reasoning
Yes
Structured outputs
Yes

Capabilities and limits as listed by models.dev.

Similarly priced models

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does Grok 4.6 cost per month?
For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Grok 4.6 costs about $1,500 per month at xAI's list prices ($2.00 per 1M input tokens, $6.00 per 1M output tokens).
Does Grok 4.6 support prompt caching?
Yes. Cached input costs $0.50 per 1M tokens, compared with $2.00 for regular input.
How long is Grok 4.6's context window?
Grok 4.6 accepts up to 500,000 tokens (500K) of context and returns up to 500,000 tokens per response.