Grok 4.5
xai / grok-4-5 / official pricing
Context 500k · Max output 0k · Last verified 2026-09-15
Standard pricing (per 1M tokens)
| Tier | Input | Output |
|---|---|---|
| Standard | $2.00 | $6.00 |
| Long context (> 200k) | $4.00 | $12.00 |
Prompt caching
| Type | Price / 1M |
|---|---|
| Cache type | automatic |
| Cache read (hit) | $0.30 |
Want to model your real cache savings? Try the cache calculator with this model selected.
Capabilities
caching tool use vision reasoning batch extended thinking
Notes & extras
- Reasoning tokens: billed as output
- Tiered pricing. A request whose prompt reaches 200k tokens is billed at the higher rate for every token in the request, not just the tokens above the threshold. Token counts are approximated with o200k_base; xAI's tokenizer is not runnable in the browser.
Sources
Found a price wrong? Report it