grok-4.6 API pricing, context and limits

Q: What is the exact API model identifier?

Use grok-4.6 exactly as shown in the provider model reference. Display names are not interchangeable with API identifiers.

Q: How much does this model cost?

The current verified prices and billing units are listed in the pricing table above. Cache, batch, tier and region conditions remain separate rows when the provider documents them.

Q: How much input can the model accept?

The model card shows the documented context window and maximum output when available. Your request must leave room for both input and generated output, including any provider-specific reasoning allocation.

Q: Can I use a free tier?

Check the linked provider free-tier page for eligibility and account conditions. An account credit or temporary trial does not establish a permanent free rate.

Q: Where do these model facts come from?

Official provider references are linked beside the data and in Sources. Changes are recorded with observation times; unresolved or undocumented fields are left unavailable.

xAI · Active

grok-4.6

grok-4.6

Context window: 500,000 tokens
Maximum output: Not documented
Input price: $2 per 1M tokens
Output price: $6 per 1M tokens
Modalities: text, image

Last verified 12 Sep 2026 · Source ↗

Official description

This model is listed in the official Text API catalog. Its request pricing distinguishes short and long context.

Read the official model reference ↗.

Where this model fits

grok-4.6 is part of the xAI API catalog. Its documented modalities are text, image. Choose it against the request format, output requirements and operational limits of your application.

For a repeatable evaluation, use representative requests, inspect structured output or tool calls, and log latency and usage in your own account. Catalog metadata establishes compatibility; it does not measure answer quality on your workload. Start from the provider guide for authentication and endpoint setup.

Current pricing

Verified model prices
Model	Price type	USD	Unit	Tier	Region	Source
grok-4.6	Cached Input	$1	per 1M tokens	long context	See source	Official source ↗
grok-4.6	Cached Input	$1	per 1M tokens	long context ≥200k	See source	Official source ↗
grok-4.6	Cached Input	$0.5	per 1M tokens	short context	See source	Official source ↗
grok-4.6	Cached Input	$0.5	per 1M tokens	short context <200k	See source	Official source ↗
grok-4.6	Input	$4	per 1M tokens	long context	See source	Official source ↗
grok-4.6	Input	$4	per 1M tokens	long context ≥200k	See source	Official source ↗
grok-4.6	Input	$2	per 1M tokens	short context	See source	Official source ↗
grok-4.6	Input	$2	per 1M tokens	short context <200k	See source	Official source ↗
grok-4.6	Output	$12	per 1M tokens	long context	See source	Official source ↗
grok-4.6	Output	$12	per 1M tokens	long context ≥200k	See source	Official source ↗
grok-4.6	Output	$6	per 1M tokens	short context	See source	Official source ↗
grok-4.6	Output	$6	per 1M tokens	short context <200k	See source	Official source ↗

Last verified 12 Sep 2026 · Source ↗

Estimate request, daily and monthly usage in the API cost calculator.

Rate limits and availability

Verified rate limits
Model or scope	Tier	Metric	Limit	Notes	Source
grok-4.6 `grok-4.6`	Tier 0	RPM	9,000	Normalized from published requests per second ×60; the per-second gate still applies.	Official source ↗
grok-4.6 `grok-4.6`	Tier 0	TPM	50,000,000	Published tokens per minute.	Official source ↗
grok-4.6 `grok-4.6`	Tier 1	RPM	10,320	Normalized from published requests per second ×60; the per-second gate still applies.	Official source ↗
grok-4.6 `grok-4.6`	Tier 1	TPM	53,000,000	Published tokens per minute.	Official source ↗
grok-4.6 `grok-4.6`	Tier 2	RPM	12,480	Normalized from published requests per second ×60; the per-second gate still applies.	Official source ↗
grok-4.6 `grok-4.6`	Tier 2	TPM	60,000,000	Published tokens per minute.	Official source ↗
grok-4.6 `grok-4.6`	Tier 3	RPM	18,720	Normalized from published requests per second ×60; the per-second gate still applies.	Official source ↗
grok-4.6 `grok-4.6`	Tier 3	TPM	74,000,000	Published tokens per minute.	Official source ↗
grok-4.6 `grok-4.6`	Tier 4	RPM	30,000	Normalized from published requests per second ×60; the per-second gate still applies.	Official source ↗
grok-4.6 `grok-4.6`	Tier 4	TPM	100,000,000	Published tokens per minute.	Official source ↗

Last verified 12 Sep 2026 · Source ↗

Account-specific capacity may differ. Check the provider rate-limit guide and the free-tier conditions.

Three alternatives to compare

These alternatives share a documented modality and have the closest combination of input price and context size in the current catalog. This is a specification comparison, not a quality benchmark.

Computed model alternatives
Model	Provider	Input / 1M tokens	Context
grok-4.5	xAI	$2	500,000
SpaceXAI: Grok 4.5	OpenRouter	$2	500,000
SpaceXAI: Grok 4.6	OpenRouter	$2	500,000

Use the exact identifier in Python

This identifier fragment belongs in the authenticated request described in the provider Python tutorial. The tutorial covers the correct SDK, endpoint, environment variable and response shape.

model = "grok-4.6"
# Pass model to the provider-specific request in the tutorial.

Recent changes

12 September 2026

xAI · grok-4.6 — MetadataRecord updated; consult the linked source for details. → Record updated; consult the linked source for details.Source ↗
xAI · grok-4.6 — MetadataRecord updated; consult the linked source for details. → Record updated; consult the linked source for details.Source ↗
xAI · grok-4.6 — MetadataRecord updated; consult the linked source for details. → Record updated; consult the linked source for details.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 4 · Metric: TPM · Value: 100000000 · Notes: Published tokens per minute.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 3 · Metric: TPM · Value: 74000000 · Notes: Published tokens per minute.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 2 · Metric: TPM · Value: 60000000 · Notes: Published tokens per minute.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 1 · Metric: TPM · Value: 53000000 · Notes: Published tokens per minute.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 0 · Metric: TPM · Value: 50000000 · Notes: Published tokens per minute.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 4 · Metric: RPM · Value: 30000 · Notes: Normalized from published requests per second ×60; the per-second gate still applies.Source ↗
xAI · grok-4.6 — ValueNot previously recorded → Tier: Tier 3 · Metric: RPM · Value: 18720 · Notes: Normalized from published requests per second ×60; the per-second gate still applies.Source ↗

Subscribe to the changelog RSS feed

Frequently asked questions

What is the exact API model identifier?

Use grok-4.6 exactly as shown in the provider model reference. Display names are not interchangeable with API identifiers.

How much does this model cost?

The current verified prices and billing units are listed in the pricing table above. Cache, batch, tier and region conditions remain separate rows when the provider documents them.

How much input can the model accept?

The model card shows the documented context window and maximum output when available. Your request must leave room for both input and generated output, including any provider-specific reasoning allocation.

Can I use a free tier?

Check the linked provider free-tier page for eligibility and account conditions. An account credit or temporary trial does not establish a permanent free rate.

Where do these model facts come from?

Official provider references are linked beside the data and in Sources. Changes are recorded with observation times; unresolved or undocumented fields are left unavailable.

Sources

Last verified 12 Sep 2026 · Source ↗