Approved models
11
Records published from this collection
Provider information
inference host
Review approach
Verify each model’s source, terms, capabilities, and current availability
Xai via Requesty models in this directory cover text-to-text ai models. Start with the task you need to solve, then open a model profile to check its recorded inputs, outputs, licensing and deployment options.
Use inputs that resemble deployment traffic, including difficult and out-of-domain cases. Compare output correctness, the response format, latency and memory requirements with a simple baseline under the same conditions. For hosted models, confirm the model ID, current API access, data controls and applicable pricing tier before routing production traffic.
Check whether two entries describe distinct models or different hosted routes for the same model. Keep the checkpoint, host, test settings and evaluation date together. Missing prices and limits mean the directory has no recorded figure, not that use is free or unlimited.
Browse the AI model directory or compare two models.
Review each record individually; collection membership does not imply a recommendation or guarantee of availability.
| Grok 4 1 Fast Non Reasoning Xai via Requesty | 59.5 | 2M | $0.20 | $0.50 | — |
| Grok 4 1 Fast Reasoning Xai via Requesty | 74.5 | 2M | $0.20 | $0.50 | — |
| Grok 4 Fast Non Reasoning Xai via Requesty | 57.3 | 2M | $0.20 | $0.50 | — |
| Grok Code Fast 1 Xai via Requesty | 67.2 | 256K | $0.20 | $1.50 | — |
| Grok 4 Xai via Requesty | 67.0 | 256K | $3.00 | $15.00 | — |
| Grok 3 Xai via Requesty | 37.3 | 131.07K | $5.00 | $25.00 | — |
| Grok 3 Mini Xai via Requesty | 52.3 | 131.07K | $0.30 | $0.50 | — |
| Grok 3 Mini:High Xai via Requesty | 46.8 | 131.07K | $0.30 | $0.50 | — |
| Grok 3 Mini:Low Xai via Requesty | 46.8 | 131.07K | $0.30 | $0.50 | — |
| Grok 4 Fast Xai via Requesty | 45.0 | 2M | $0.20 | $0.50 | — |
| Grok 4.2 Beta Xai via Requesty | 65.0 | 2M | $2.00 | $6.00 | — |
1–11 of 11 models · select a column to sort
About this order: Recommended shows our editorial shortlist first, followed by recent releases. The spec score is a 0–100 figure SyncDev calculates from each vendor's published specifications — context window, reasoning support, input modalities, tool calling, maximum output and how recently the model shipped. It measures breadth of capability, not benchmark performance, so a higher-scoring model is not automatically the better choice for your task.