Grok 4.3 vs Grok 4.6: API price and specs

Grok 4.3 is 38% cheaper than Grok 4.6 on input price.

Grok 4.3 is 58% cheaper than Grok 4.6 on output price.

Grok 4.3 is 45% cheaper than Grok 4.6 on a 1M-in / 200k-out workload.

Grok 4.6 has a 100% larger context than Grok 4.3.

Field	Grok 4.3	Grok 4.6
Lowest input, per 1M	$1.00	$1.60 +60%
Median input, per 1M	$1.25	$2.00 +60%
Lowest output, per 1M	$2.00	$4.80 +140%
Median output, per 1M	$2.50	$6.00 +140%
Lowest unit price	—	—
Cost of 1M in + 200k out	$1.40	$2.56 +82.9%
Context	1M +50%	2M
Max output	1M	500K +50%
Providers	24 +14.3%	28
Regions	US	GLOBAL, US
Accepts	application/pdf, file, image, image/jpeg, image/png, pdf, text	file, image, image/jpeg, image/png, pdf, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	cometapi	cometapi

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

302ai, abacus, aihubmix, aiml, amazon-bedrock, cometapi, edenai, fastrouter, google-vertex, impossibl, jiekou, kilo, meganova, ofox, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, xai, zenmux

Frequently asked questions

Which is cheaper, Grok 4.3 or Grok 4.6?

Grok 4.3 is 38% cheaper than Grok 4.6 on input price. Grok 4.3 is 58% cheaper than Grok 4.6 on output price. Grok 4.3 is 45% cheaper than Grok 4.6 on a 1M-in / 200k-out workload.

Which has the larger context, Grok 4.3 or Grok 4.6?

Grok 4.3: 1M tokens; Grok 4.6: 2M tokens.

Where can I use both Grok 4.3 and Grok 4.6?