Grok Models
Usage
0
4
3 of 24
- grok-4-1-fast-non-reasoning
- grok-4-1-fast-reasoning
- grok-build-0.1
Which models that traffic went to
- grok-4-1-fast-non-reasoning50.0%2
- Grok 4.1 Fast (reasoning)25.0%1
- Grok Build 0.125.0%1
All 24 Grok Models
Open in model list| Modalities | |||||||
|---|---|---|---|---|---|---|---|
| grok-4-1-fast-non-reasoning | Takes text, vision, returns text. | 1M | 2M | $0.2$0.5/M | $0.05/M | — | — |
| grok-4-1-fast-reasoning | Takes text, vision, returns text. | 1M | 2M | $0.2$0.5/M | $0.05/M | — | — |
| grok-4-fast-non-reasoning | Takes text, vision. Output modality not published. | 1M | — | $0.2$0.5/M | $0.05/M | 137 tok/s | 2.70 s |
| grok-4-fast-reasoning | Takes text, vision. Output modality not published. | 1M | — | $0.2$0.5/M | $0.05/M | 137 tok/s | 2.70 s |
| grok-4.3 | Takes text, vision. Output modality not published. | 1M | — | $1.25$2.5/M | $0.2/M | — | — |
| grok-4.5 | Takes text, vision. Output modality not published. | 500K | — | $2$6/M | $0.5/M | — | — |
| grok-code-fast-1 | Takes text, vision. Output modality not published. | 256K | — | $0.2$1.5/M | $0.02/M | 87 tok/s | 1.26 s |
| grok-build-0.1 | Takes text, vision, returns text. | 256K | 2M | $1$2/M | $0.2/M | 36 tok/s | 0.80 s |
| grok-4 | Takes text, vision. Output modality not published. | 256K | — | $3.3$16.5/M | $0.825/M | 54 tok/s | 2.70 s |
| grok-3-mini | — | — | $0.3$0.501/M | — | — | — | |
| grok-3-mini-beta | — | — | $0.33$0.5511/M | — | — | — | |
| grok-3-mini-fast-beta | — | — | $0.33$2.2001/M | — | — | — | |
| grok-4.20-0309-non-reasoning | — | — | $1.25$2.5/M | $0.2/M | — | — | |
| grok-2-1212 | — | — | $1.8$9/M | — | — | — | |
| grok-2-vision-1212 | Takes text, vision, returns text. | — | — | $1.8$9/M | — | — | — |
| grok-4.20-beta-0309-non-reasoning | — | — | $2$6/M | $0.2/M | — | — | |
| grok-4.20-beta-0309-reasoning | — | — | $2$6/M | $0.2/M | — | — | |
| grok-4.20-multi-agent-beta-0309 | — | — | $2$6/M | $0.2/M | — | — | |
| grok-3 | — | — | $3$15/M | — | — | — | |
| grok-3-beta | — | — | $3$15/M | — | — | — | |
| grok-3-fast | — | — | $5.5$27.5/M | — | — | — | |
| grok-3-fast-beta | — | — | $5.5$27.5/M | — | — | — | |
| grok-vision-beta | Takes text, vision, returns text. | — | — | $5.6$16.8/M | — | — | — |
| grok-4-pro | — | — | $60$300/M | $15/M | 54 tok/s | 2.70 s |
Grok on AIHubMix
Which Grok model should I start with?
grok-4-1-fast-non-reasoning at $0.2/M input — the cheapest entry here that declares tool calling, and it carries a 1M context. Move up to grok-4-pro when answer quality matters more than cost, or to grok-4-1-fast-reasoning for long-form reasoning.
Which of these models reason before answering?
3 of the 24 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.
Why are there several entries for the same model?
Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.
The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.
How is cached input billed?
The Cache read column is the rate for input tokens served from the prompt cache — for example grok-4.20-beta-0309-non-reasoning bills cache hits at 10% of the input rate and grok-4.20-beta-0309-reasoning bills cache hits at 10% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.
Do I need a separate Grok account?
No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.
Start calling Grok in one line
One key, one endpoint, 750 models across 29 model authors.
