#156
XA
Grok 1.5
xAI
19.3 LLMBoard
xAI model product
Grok 4.3 is xAI's newest flagship general-purpose model. xAI describes it as the most intelligent and fastest model it has built, with a 1 million token context window, reasoning support, function calling, structured outputs, prompt caching, and industry-leading non-hallucination, agentic tool calling, and instruction-following capabilities.
Updated Aug 10, 2026. Default version: Grok 4.3
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
No published version under this unique model currently has enough benchmark coverage to calculate a score.
Published benchmark records for the scored version currently unavailable.
No published benchmark result is linked to the scored version.
Preference and agent-evaluation signals from published Arena datasets.
| search style control | overall | 16 | 1190.5 | 68,373 | N/A | |
| vision style control | entity recognition | 16 | 1226.9 | 97 | N/A | |
| search factuality | overall | 19 | 1173.3 | 68,373 | N/A | |
| search | overall | 21 | 1163.2 | 68,373 | N/A | |
| vision | entity recognition | 23 | 1233.4 | 97 | N/A | |
| vision style control | creative writing vision | 26 | 1259.1 | 1,013 | N/A | |
| text factuality | japanese | 30 | 1402.1 | 405 | N/A | |
| vision style control | humor | 37 | 1237.1 | 628 | N/A | |
| text factuality | korean | 38 | 1354.9 | 396 | N/A | |
| webdev | image to webdev | 38 | 1374.9 | 4,110 | N/A | |
| vision style control | chinese | 40 | 1286.0 | 894 | N/A | |
| vision style control | english | 42 | 1247.4 | 7,714 | N/A | |
| text factuality | polish | 43 | 1395.5 | 542 | N/A | |
| vision | creative writing vision | 43 | 1248.0 | 1,013 | N/A | |
| vision style control | overall | 44 | 1244.3 | 18,132 | N/A | |
| vision style control | diagram | 45 | 1268.1 | 4,914 | N/A | |
| vision | humor | 46 | 1232.2 | 628 | N/A | |
| vision style control | ocr | 48 | 1252.5 | 13,111 | N/A | |
| text style control | japanese | 51 | 1421.1 | 530 | N/A | |
| vision style control | homework | 51 | 1255.8 | 2,414 | N/A | |
| vision | chinese | 53 | 1264.8 | 894 | N/A | |
| text style control | polish | 55 | 1447.9 | 961 | N/A | |
| text factuality | french | 59 | 1442.3 | 1,567 | N/A | |
| text factuality | spanish | 59 | 1415.0 | 1,194 | N/A | |
| text style control | creative writing | 59 | 1427.4 | 9,122 | N/A | |
| vision | english | 59 | 1237.2 | 7,714 | N/A | |
| vision | homework | 59 | 1243.3 | 2,414 | N/A | |
| vision | overall | 60 | 1231.3 | 18,132 | N/A | |
| vision | ocr | 61 | 1236.9 | 13,111 | N/A | |
| vision | diagram | 63 | 1242.5 | 4,914 | N/A | |
| text style control | korean | 64 | 1397.4 | 804 | N/A | |
| text style control | industry entertainment and sports and media | 65 | 1417.2 | 12,176 | N/A | |
| text style control | chinese | 66 | 1485.1 | 2,858 | N/A | |
| text style control | german | 66 | 1442.8 | 769 | N/A | |
| text style control | russian | 69 | 1444.3 | 5,311 | N/A | |
| text style control | industry writing and literature and language | 70 | 1424.1 | 13,215 | N/A | |
| text style control | english | 71 | 1451.3 | 24,970 | N/A | |
| webdev | webdev-react | 71 | 1353.0 | 8,673 | N/A | |
| text style control | french | 72 | 1461.2 | 2,009 | N/A | |
| text style control | spanish | 72 | 1434.7 | 1,535 | N/A | |
| text factuality | industry mathematical | 73 | 1416.3 | 2,226 | N/A | |
| text style control | industry life and physical and social science | 74 | 1458.2 | 8,744 | N/A | |
| text style control | industry software and it services | 74 | 1478.9 | 21,397 | N/A | |
| text style control | non english | 74 | 1428.2 | 28,263 | N/A | |
| text factuality | russian | 75 | 1432.6 | 4,329 | N/A | |
| text style control | overall | 75 | 1441.6 | 53,234 | N/A | |
| text style control | exclude ties | 75 | 1440.6 | 40,849 | N/A | |
| text factuality | chinese | 76 | 1455.5 | 2,309 | N/A | |
| text factuality | creative writing | 76 | 1409.9 | 8,086 | N/A | |
| text factuality | math | 76 | 1413.7 | 2,020 | N/A | |
| text style control | coding | 77 | 1487.7 | 15,091 | N/A | |
| webdev | webdev-html | 77 | 1361.2 | 1,274 | N/A | |
| text style control | multi turn | 78 | 1447.4 | 9,754 | N/A | |
| text style control | longer query | 79 | 1445.2 | 23,685 | N/A | |
| webdev | overall | 79 | 1356.8 | 10,856 | N/A | |
| webdev | webdev | 79 | 1356.8 | 10,856 | N/A | |
| text style control | industry business and management and financial operations | 80 | 1439.5 | 10,725 | N/A | |
| text factuality | industry writing and literature and language | 81 | 1413.9 | 12,620 | N/A | |
| text factuality | multi turn | 82 | 1438.1 | 8,480 | N/A | |
| text factuality | industry entertainment and sports and media | 84 | 1402.3 | 11,489 | N/A | |
| text style control | hard prompts | 84 | 1456.4 | 35,374 | N/A | |
| text style control | hard prompts english | 84 | 1461.3 | 17,188 | N/A | |
| text style control | industry medicine and healthcare | 84 | 1455.8 | 3,957 | N/A | |
| text | japanese | 85 | 1374.2 | 530 | N/A | |
| text factuality | industry legal and government | 88 | 1431.9 | 3,457 | N/A | |
| text style control | industry legal and government | 88 | 1440.1 | 4,271 | N/A | |
| text factuality | expert | 90 | 1436.7 | 4,406 | N/A | |
| text style control | expert | 91 | 1452.6 | 5,268 | N/A | |
| text factuality | industry medicine and healthcare | 92 | 1442.1 | 3,182 | N/A | |
| text factuality | longer query | 93 | 1438.9 | 23,170 | N/A | |
| text factuality | non english | 94 | 1414.7 | 28,221 | N/A | |
| text style control | industry mathematical | 94 | 1434.0 | 2,811 | N/A | |
| text factuality | coding | 96 | 1469.5 | 14,563 | N/A | |
| text factuality | industry life and physical and social science | 96 | 1445.7 | 7,702 | N/A | |
| text factuality | overall | 98 | 1428.4 | 53,166 | N/A | |
| text factuality | exclude ties | 100 | 1420.1 | 40,796 | N/A | |
| text factuality | hard prompts | 100 | 1446.3 | 35,329 | N/A | |
| text factuality | industry software and it services | 100 | 1460.2 | 21,082 | N/A | |
| text factuality | hard prompts english | 101 | 1451.1 | 16,651 | N/A | |
| text | polish | 102 | 1401.3 | 961 | N/A | |
| text factuality | english | 102 | 1436.9 | 24,934 | N/A | |
| text factuality | instruction following | 102 | 1410.0 | 17,669 | N/A | |
| text style control | instruction following | 104 | 1414.4 | 18,209 | N/A | |
| text style control | math | 104 | 1419.7 | 2,589 | N/A | |
| text | german | 105 | 1399.7 | 769 | N/A | |
| text | russian | 105 | 1403.6 | 5,311 | N/A | |
| text factuality | industry business and management and financial operations | 105 | 1422.9 | 9,644 | N/A | |
| text | creative writing | 106 | 1386.8 | 9,122 | N/A | |
| text | korean | 116 | 1351.0 | 804 | N/A | |
| text | french | 117 | 1411.6 | 2,009 | N/A | |
| text | industry writing and literature and language | 117 | 1386.6 | 13,215 | N/A | |
| text | industry entertainment and sports and media | 118 | 1373.5 | 12,176 | N/A | |
| text | multi turn | 118 | 1406.9 | 9,754 | N/A | |
| text | spanish | 119 | 1395.8 | 1,535 | N/A | |
| text | chinese | 124 | 1431.9 | 2,858 | N/A | |
| text | coding | 127 | 1415.5 | 15,091 | N/A | |
| text | longer query | 128 | 1397.1 | 23,685 | N/A | |
| text | non english | 129 | 1387.0 | 28,263 | N/A | |
| text | industry software and it services | 130 | 1416.4 | 21,397 | N/A | |
| text | exclude ties | 131 | 1379.5 | 40,849 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| DaoXE | grok-4.3 | global | $1.25 | $2.5 | 1M | |
| Abacus | grok-4.3 | global | $1.25 | $2.5 | 1M | |
| Auriko | grok-4.3 | global | $1.25 | $2.5 | 1M | |
| xAI | grok-4.3 | global | $1.25 | $2.5 | 1M | |
| AIHubMix | grok-4.3 | global | $1.25 | $2.5 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Grok 4.3 | N/A | N/A | 1M | 30K | No | Proprietary |
A concise description based on the published model registry.
Grok 4.3 is xAI's newest flagship general-purpose model. xAI describes it as the most intelligent and fastest model it has built, with a 1 million token context window, reasoning support, function calling, structured outputs, prompt caching, and industry-leading non-hallucination, agentic tool calling, and instruction-following capabilities.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Grok 4.3.
Grok 4.3's default version was released on May 6, 2026.
Grok 4.3's official API price is $1.25 per million input tokens and $2.5 per million output tokens via xAI. The lowest tracked third-party offer starts at $1.25 input and $2.5 output via DaoXE.
Grok 4.3 is published under xAI in the model registry.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
5 published provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.