Grok 4.3 pricing
API list price by xAI · same on AWS Bedrock, x-ai · checked Oct 26, 2026
$1.25 / $2.50per 1M tokens in / out
$0.20cache read · −84%
#128on OpenRouter by tokens · 38.2B / week
Price sheetper 1M tokens
| Input | $1.25 | list |
| Output | $2.50 | |
| Cache read | $0.20 | −84% vs input |
| Context · max output | 1M · 900K | tokens |
Cost per task by effort?
non-thinking$0.156.8
high$0.2137.2
per taskHumanity's Last Exam
Same price per token at every effort; the bill grows with reasoning tokens. high costs 1.4× medium for +7.2 points.
Where to buy3 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| AWS Bedrock | $1.25 | $2.50 | — |
| x-ai | $1.25 | $2.50 | — |
| xAIlab | $1.25 | $2.50 | 1M |
In xAI's line-upper 1M in / out
| Grok 4.3 | $1.25 / $2.50 | this model |
| Grok 4.20 Multi-Agent | $1.25 / $2.50 | 0% |
| Grok 4.20 Non-Reasoning | $1.25 / $2.50 | 0% |
| Grok 4.20 Reasoning | $1.25 / $2.50 | 0% |
| Grok 4.20 0309 Non Reasoning | $1.25 / $2.50 | 0% |
| Grok 4.20 0309 Reasoning | $1.25 / $2.50 | 0% |
| Grok 4.20 Multi Agent 0309 | $1.25 / $2.50 | 0% |
Cheaper for the same workvs Grok 4.3 at medium
| MiMo v2.6 Pro thinkingOpen | -65% | score +87% | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -66% | score +82% | $0.26 |
| Ling 3.1 Flash 1019 | -71% | score +77% | $1.49 |
| Step 5 Preview thinkingOpen | -9% | score +76% | $1.03 |
| Claude Haiku 5.5 max | -87% | score +75% | $0.21 |
Pricing questions
How much does Grok 4.3 cost?›
$1.25 per 1M input tokens and $2.50 per 1M output tokens on xAI's API and AWS Bedrock, x-ai. Cached input is $0.20.
Is Grok 4.3 free to use?›
There is no free API tier.
How much does prompt caching save?›
Cache reads cost $0.20 per 1M, 84% below the input price.
Is Grok 4.3 cheaper than Grok 4.20?›
It costs the same per token: $1.25 / $2.50.
How does effort change the price?›
The price per token is the same at every effort. Higher effort spends more reasoning tokens: a task costs $0.15 at non-thinking, $0.21 at high.
What is a cheaper alternative to Grok 4.3?›
MiMo v2.6 Pro at thinking effort costs -65% per task with a score +87% on Humanity's Last Exam.