ColinBuilds · Official xAI API pricing
Grok 4.6
- Input / 1M
- $2.00
- Output / 1M
- $6.00
- Official xAI context window
- 500,000 tokens
xAI grok-4.6 official API pricing for prompts under 200k tokens: $2.00 input, $0.50 cached input, and $6.00 output per 1M tokens. Prompts at or above 200k tokens are $4.00 / $1.00 / $12.00 for the full request. Context window 500k tokens. · as of August 25, 2026
Compare models
Same per-1M input/output rates as above. Enter your monthly token volumes to compare bills.
Grok 4.6
- Input: 1M × $2.00 = $2.00
- Output: 1M × $6.00 = $6.00
- Total
- $8.00
GPT-4o
- Input: 1M × $2.50 = $2.50
- Output: 1M × $10.00 = $10.00
- Total
- $12.50
Difference
$4.50
GPT-4o costs $4.50 more than Grok 4.6.
Popular comparisons
37 total featuring Grok 4.6.
Grok 4.6 is xAI’s current flagship API model for code and general work, with agentic tool calling, configurable reasoning, and official xAI token pricing.
What this model is
xAI lists the exact model name as grok-4.6. The models overview describes it as the flagship model for code and everything else: agentic tool calling, minimal hallucinations, and configurable reasoning. xAI’s model-choice guidance says to use Grok 4.6 for code and chat.
The official model page lists text and image input with text output, a 500,000-token context window, function calling, structured outputs, and reasoning. Batch API is listed as not supported. The knowledge cutoff is February 1, 2026.
Grok 4.3 remains available as a previous Grok 4-line route with a larger 1M context window and different token prices.
Pricing notes
xAI’s official Grok 4.6 model page lists API pricing for prompts under 200k tokens at $2.00 per 1M input tokens, $0.50 per 1M cached input tokens, and $6.00 per 1M output tokens.
For prompts at or above 200k tokens, the same page lists $4.00 input, $1.00 cached input, and $12.00 output per 1M tokens, billed at the higher rate for all tokens in the request.
The calculator on this page uses the under-200k uncached input and output rates: $2.00 input and $6.00 output per 1M tokens.
Benchmarks and specs
xAI’s model page lists Grok 4.6 with a 500,000 token context window, text and image input, text output, function calling, structured outputs, and reasoning. Batch API is not supported.
This page does not show a parameter count or public benchmark score. Those numbers should only be shown when exact public sources are matched to grok-4.6 specifically.
Best fit
Grok 4.6 is best for builders who want xAI’s current flagship API route for coding, assistants, tool-using agents, and general knowledge work.
Use Grok 4.3 when the job needs the older 1M-context Grok 4.3 snapshot. Use Grok Build 0.1 when the job is specifically xAI’s coding-oriented Build route.