|
1308 | 1308 | "mode": "chat"
|
1309 | 1309 | },
|
1310 | 1310 | "azure_ai/mistral-large-2407": {
|
1311 |
| - "max_tokens": 128000, |
| 1311 | + "max_tokens": 4096, |
1312 | 1312 | "max_input_tokens": 128000,
|
1313 | 1313 | "max_output_tokens": 4096,
|
1314 | 1314 | "input_cost_per_token": 0.000002,
|
|
1319 | 1319 | "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview"
|
1320 | 1320 | },
|
1321 | 1321 | "azure_ai/ministral-3b": {
|
1322 |
| - "max_tokens": 128000, |
| 1322 | + "max_tokens": 4096, |
1323 | 1323 | "max_input_tokens": 128000,
|
1324 | 1324 | "max_output_tokens": 4096,
|
1325 | 1325 | "input_cost_per_token": 0.00000004,
|
|
1330 | 1330 | "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview"
|
1331 | 1331 | },
|
1332 | 1332 | "azure_ai/Llama-3.2-11B-Vision-Instruct": {
|
1333 |
| - "max_tokens": 128000, |
| 1333 | + "max_tokens": 2048, |
1334 | 1334 | "max_input_tokens": 128000,
|
1335 | 1335 | "max_output_tokens": 2048,
|
1336 | 1336 | "input_cost_per_token": 0.00000037,
|
|
1342 | 1342 | "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview"
|
1343 | 1343 | },
|
1344 | 1344 | "azure_ai/Llama-3.3-70B-Instruct": {
|
1345 |
| - "max_tokens": 128000, |
| 1345 | + "max_tokens": 2048, |
1346 | 1346 | "max_input_tokens": 128000,
|
1347 | 1347 | "max_output_tokens": 2048,
|
1348 | 1348 | "input_cost_per_token": 0.00000071,
|
1349 | 1349 | "output_cost_per_token": 0.00000071,
|
1350 | 1350 | "litellm_provider": "azure_ai",
|
1351 | 1351 | "supports_function_calling": true,
|
1352 |
| - "supports_vision": true, |
1353 | 1352 | "mode": "chat",
|
1354 | 1353 | "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview"
|
1355 | 1354 | },
|
1356 | 1355 | "azure_ai/Llama-3.2-90B-Vision-Instruct": {
|
1357 |
| - "max_tokens": 128000, |
| 1356 | + "max_tokens": 2048, |
1358 | 1357 | "max_input_tokens": 128000,
|
1359 | 1358 | "max_output_tokens": 2048,
|
1360 | 1359 | "input_cost_per_token": 0.00000204,
|
|
1366 | 1365 | "source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview"
|
1367 | 1366 | },
|
1368 | 1367 | "azure_ai/Meta-Llama-3-70B-Instruct": {
|
1369 |
| - "max_tokens": 8192, |
| 1368 | + "max_tokens": 2048, |
1370 | 1369 | "max_input_tokens": 8192,
|
1371 |
| - "max_output_tokens": 8192, |
| 1370 | + "max_output_tokens": 2048, |
1372 | 1371 | "input_cost_per_token": 0.0000011,
|
1373 | 1372 | "output_cost_per_token": 0.00000037,
|
1374 | 1373 | "litellm_provider": "azure_ai",
|
1375 | 1374 | "mode": "chat"
|
1376 | 1375 | },
|
1377 | 1376 | "azure_ai/Meta-Llama-3.1-8B-Instruct": {
|
1378 |
| - "max_tokens": 128000, |
| 1377 | + "max_tokens": 2048, |
1379 | 1378 | "max_input_tokens": 128000,
|
1380 |
| - "max_output_tokens": 128000, |
| 1379 | + "max_output_tokens": 2048, |
1381 | 1380 | "input_cost_per_token": 0.0000003,
|
1382 | 1381 | "output_cost_per_token": 0.00000061,
|
1383 | 1382 | "litellm_provider": "azure_ai",
|
1384 | 1383 | "mode": "chat",
|
1385 | 1384 | "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice"
|
1386 | 1385 | },
|
1387 | 1386 | "azure_ai/Meta-Llama-3.1-70B-Instruct": {
|
1388 |
| - "max_tokens": 128000, |
| 1387 | + "max_tokens": 2048, |
1389 | 1388 | "max_input_tokens": 128000,
|
1390 |
| - "max_output_tokens": 128000, |
| 1389 | + "max_output_tokens": 2048, |
1391 | 1390 | "input_cost_per_token": 0.00000268,
|
1392 | 1391 | "output_cost_per_token": 0.00000354,
|
1393 | 1392 | "litellm_provider": "azure_ai",
|
1394 | 1393 | "mode": "chat",
|
1395 | 1394 | "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice"
|
1396 | 1395 | },
|
1397 | 1396 | "azure_ai/Meta-Llama-3.1-405B-Instruct": {
|
1398 |
| - "max_tokens": 128000, |
| 1397 | + "max_tokens": 2048, |
1399 | 1398 | "max_input_tokens": 128000,
|
1400 |
| - "max_output_tokens": 128000, |
| 1399 | + "max_output_tokens": 2048, |
1401 | 1400 | "input_cost_per_token": 0.00000533,
|
1402 | 1401 | "output_cost_per_token": 0.000016,
|
1403 | 1402 | "litellm_provider": "azure_ai",
|
1404 | 1403 | "mode": "chat",
|
1405 | 1404 | "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice"
|
1406 | 1405 | },
|
1407 | 1406 | "azure_ai/Phi-3.5-mini-instruct": {
|
1408 |
| - "max_tokens": 128000, |
| 1407 | + "max_tokens": 4096, |
1409 | 1408 | "max_input_tokens": 128000,
|
1410 | 1409 | "max_output_tokens": 4096,
|
1411 | 1410 | "input_cost_per_token": 0.00000013,
|
|
1416 | 1415 | "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
|
1417 | 1416 | },
|
1418 | 1417 | "azure_ai/Phi-3.5-vision-instruct": {
|
1419 |
| - "max_tokens": 128000, |
| 1418 | + "max_tokens": 4096, |
1420 | 1419 | "max_input_tokens": 128000,
|
1421 | 1420 | "max_output_tokens": 4096,
|
1422 | 1421 | "input_cost_per_token": 0.00000013,
|
|
1427 | 1426 | "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
|
1428 | 1427 | },
|
1429 | 1428 | "azure_ai/Phi-3.5-MoE-instruct": {
|
1430 |
| - "max_tokens": 128000, |
| 1429 | + "max_tokens": 4096, |
1431 | 1430 | "max_input_tokens": 128000,
|
1432 | 1431 | "max_output_tokens": 4096,
|
1433 | 1432 | "input_cost_per_token": 0.00000016,
|
|
1449 | 1448 | "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
|
1450 | 1449 | },
|
1451 | 1450 | "azure_ai/Phi-3-mini-128k-instruct": {
|
1452 |
| - "max_tokens": 128000, |
| 1451 | + "max_tokens": 4096, |
1453 | 1452 | "max_input_tokens": 128000,
|
1454 | 1453 | "max_output_tokens": 4096,
|
1455 | 1454 | "input_cost_per_token": 0.00000013,
|
|
1460 | 1459 | "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
|
1461 | 1460 | },
|
1462 | 1461 | "azure_ai/Phi-3-small-8k-instruct": {
|
1463 |
| - "max_tokens": 8192, |
| 1462 | + "max_tokens": 4096, |
1464 | 1463 | "max_input_tokens": 8192,
|
1465 | 1464 | "max_output_tokens": 4096,
|
1466 | 1465 | "input_cost_per_token": 0.00000015,
|
|
1471 | 1470 | "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
|
1472 | 1471 | },
|
1473 | 1472 | "azure_ai/Phi-3-small-128k-instruct": {
|
1474 |
| - "max_tokens": 128000, |
| 1473 | + "max_tokens": 4096, |
1475 | 1474 | "max_input_tokens": 128000,
|
1476 | 1475 | "max_output_tokens": 4096,
|
1477 | 1476 | "input_cost_per_token": 0.00000015,
|
|
1493 | 1492 | "source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
|
1494 | 1493 | },
|
1495 | 1494 | "azure_ai/Phi-3-medium-128k-instruct": {
|
1496 |
| - "max_tokens": 128000, |
| 1495 | + "max_tokens": 4096, |
1497 | 1496 | "max_input_tokens": 128000,
|
1498 | 1497 | "max_output_tokens": 4096,
|
1499 | 1498 | "input_cost_per_token": 0.00000017,
|
|
0 commit comments