GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
text->text| Provider | Region / Tag | Context | Input/M | Output/M | Uptime 1d | Latency | Quant | Cache |
|---|---|---|---|---|---|---|---|---|
| Z.AI | z-ai/fp8 | 131K | $0.600 | $2.20 | 99.98% | - | fp8 | - |
| Rank | Category | Variant | Trend | Elo | Votes |
|---|---|---|---|---|---|
| #60 | Japanese | - | 1394 | 707 | |
| #67 | Spanish | - | 1428 | 623 | |
| #93 | Expert | - | 1440 | 1,109 | |
| #98 | Instruction Following | - | 1405 | 6,163 | |
| #100 | Korean | - | 1349 | 606 | |
| #100 | Math | - | 1413 | 1,423 | |
| #101 | Industry Entertainment And Sports And Media | - | 1384 | 4,329 | |
| #101 | Industry Mathematical | - | 1418 | 1,256 | |
| #102 | Hard Prompts | - | 1433 | 11,194 | |
| #102 | Industry Business And Management And Financial Operations | - | 1411 | 4,273 | |
| #104 | Industry Medicine And Healthcare | - | 1434 | 1,380 | |
| #107 | Industry Software And It Services | - | 1444 | 8,266 | |
| #107 | Non English | - | 1397 | 12,852 | |
| #109 | Exclude Ties | - | 1397 | 17,331 | |
| #109 | Overall | - | 1411 | 24,293 | |
| #110 | Chinese | - | 1439 | 1,344 | |
| #111 | Coding | - | 1455 | 4,767 | |
| #111 | Industry Legal And Government | - | 1416 | 1,485 | |
| #111 | Longer Query | - | 1417 | 5,005 | |
| #111 | Polish | - | 1383 | 1,639 | |
| #113 | English | - | 1419 | 11,429 | |
| #113 | Multi Turn | - | 1407 | 3,899 | |
| #114 | Hard Prompts English | - | 1433 | 5,690 | |
| #114 | Industry Life And Physical And Social Science | - | 1422 | 3,878 | |
| #114 | Industry Writing And Literature And Language | - | 1383 | 5,358 | |
| #115 | French | - | 1415 | 308 | |
| #116 | Creative Writing | - | 1374 | 3,131 | |
| #117 | Russian | - | 1396 | 1,249 | |
| #125 | German | - | 1375 | 519 |