xAI API pricing — every model compared
Last verified
Every xAI model with current API pricing, in dollars per million tokens. Verified against xAI's own documentation and dated.
All xAI models
| Model | Input | Output | Cached in | Out:in |
|---|---|---|---|---|
| Grok Build 0.1 | $1.00 | $2.00 | $0.20 | 2.0× |
| Grok 4.3 | $1.25 | $2.50 | $0.20 | 2.0× |
| Grok 4.5 | $2.00 | $6.00 | $0.30 | 3.0× |
The spread
Across xAI's current models, input pricing runs from $1.00 (Grok Build 0.1) to $2.00 (Grok 4.5) per million tokens — a 2× range.
That range is the whole reason model selection matters more than prompt golfing. Moving a workload down a tier, where quality allows, changes the bill by a multiple. Shortening a prompt changes it by a percentage.
Reading these numbers
- Output costs more than input on every model here — 2.0× to 3.0×. A workload that generates a lot is priced very differently from one that reads a lot.
- Cached input is the biggest discount available. If your prompts share a stable prefix, structuring for cache hits is worth more than any model change short of a tier drop.
- Token counts are not comparable across providers. Each tokenizes differently, so the same text is a different number of tokens on xAI than elsewhere. Cross-provider price comparisons carry a margin of error.
Getting your actual spend
These are list prices. For what you are really being billed, read xAI's billing API — a management key is what that takes.
Source
Verified against xAI's pricing documentation. Each model page carries its own verification date.