Home › Providers › xAI Grok
xAI Grok API pricing
Grok 4.x models. 2 models priced per 1,000,000 tokens, verified October 2026. Cheapest: Grok 4.3 at $1.25 input. Most expensive: Grok 4.6 at $6 output.
xAI Grok price table
| Model | Input | Cached | Cache write | Output | Context | Batch |
|---|---|---|---|---|---|---|
| Grok 4.3 | $1.25 | $0.20 | — | $2.50 | 1,000,000 | Yes |
| Grok 4.6 | $2 | $0.50 | — | $6 | 500,000 | Yes |
How xAI Grok compares with other providers
| Provider | Models | Cheapest input | Cheapest output | Flagship output |
|---|---|---|---|---|
| OpenAI | 13 | $0.10 | $0.50 | $50 |
| Anthropic | 5 | $1 | $5 | $50 |
| Google Gemini | 6 | $0.30 | $2.50 | $12 |
| xAI Grok | 2 | $1.25 | $2.50 | $6 |
| DeepSeek | 2 | $0.30 | $1.20 | $3.96 |
Workload cost on xAI Grok
| Model | Support chat 1K reqs · 4K/600 | RAG + cache 1K reqs · 50K/1K | Nightly batch 10K reqs · 10K/2K |
|---|---|---|---|
| Grok 4.3 | $6.50 | $17.80 | $87.50 |
| Grok 4.6 | $11.60 | $38.57 | $160 |
FAQ
What is the cheapest xAI Grok model?
Grok 4.3 at $1.25 per 1M input and $2.50 per 1M output tokens.
What is the most expensive xAI Grok model?
Grok 4.6 at $2 per 1M input and $6 per 1M output tokens.
Does xAI Grok charge for prompt caching?
Yes. Cached reads are published per model; on this provider they range from $0.20 to $0.50 per 1M tokens.