Skip to content

Commit c90942e

Browse files
authored
Correct max_tokens on Model DB (#7284)
Corrects several instances of `max_tokens` and `max_output_tokens` for Azure AI models
1 parent f3c546b commit c90942e

File tree

1 file changed

+20
-21
lines changed

1 file changed

+20
-21
lines changed

model_prices_and_context_window.json

Lines changed: 20 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -1308,7 +1308,7 @@
13081308
"mode": "chat"
13091309
},
13101310
"azure_ai/mistral-large-2407": {
1311-
"max_tokens": 128000,
1311+
"max_tokens": 4096,
13121312
"max_input_tokens": 128000,
13131313
"max_output_tokens": 4096,
13141314
"input_cost_per_token": 0.000002,
@@ -1319,7 +1319,7 @@
13191319
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview"
13201320
},
13211321
"azure_ai/ministral-3b": {
1322-
"max_tokens": 128000,
1322+
"max_tokens": 4096,
13231323
"max_input_tokens": 128000,
13241324
"max_output_tokens": 4096,
13251325
"input_cost_per_token": 0.00000004,
@@ -1330,7 +1330,7 @@
13301330
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview"
13311331
},
13321332
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
1333-
"max_tokens": 128000,
1333+
"max_tokens": 2048,
13341334
"max_input_tokens": 128000,
13351335
"max_output_tokens": 2048,
13361336
"input_cost_per_token": 0.00000037,
@@ -1342,19 +1342,18 @@
13421342
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview"
13431343
},
13441344
"azure_ai/Llama-3.3-70B-Instruct": {
1345-
"max_tokens": 128000,
1345+
"max_tokens": 2048,
13461346
"max_input_tokens": 128000,
13471347
"max_output_tokens": 2048,
13481348
"input_cost_per_token": 0.00000071,
13491349
"output_cost_per_token": 0.00000071,
13501350
"litellm_provider": "azure_ai",
13511351
"supports_function_calling": true,
1352-
"supports_vision": true,
13531352
"mode": "chat",
13541353
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.llama-3-3-70b-instruct-offer?tab=Overview"
13551354
},
13561355
"azure_ai/Llama-3.2-90B-Vision-Instruct": {
1357-
"max_tokens": 128000,
1356+
"max_tokens": 2048,
13581357
"max_input_tokens": 128000,
13591358
"max_output_tokens": 2048,
13601359
"input_cost_per_token": 0.00000204,
@@ -1366,46 +1365,46 @@
13661365
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview"
13671366
},
13681367
"azure_ai/Meta-Llama-3-70B-Instruct": {
1369-
"max_tokens": 8192,
1368+
"max_tokens": 2048,
13701369
"max_input_tokens": 8192,
1371-
"max_output_tokens": 8192,
1370+
"max_output_tokens": 2048,
13721371
"input_cost_per_token": 0.0000011,
13731372
"output_cost_per_token": 0.00000037,
13741373
"litellm_provider": "azure_ai",
13751374
"mode": "chat"
13761375
},
13771376
"azure_ai/Meta-Llama-3.1-8B-Instruct": {
1378-
"max_tokens": 128000,
1377+
"max_tokens": 2048,
13791378
"max_input_tokens": 128000,
1380-
"max_output_tokens": 128000,
1379+
"max_output_tokens": 2048,
13811380
"input_cost_per_token": 0.0000003,
13821381
"output_cost_per_token": 0.00000061,
13831382
"litellm_provider": "azure_ai",
13841383
"mode": "chat",
13851384
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice"
13861385
},
13871386
"azure_ai/Meta-Llama-3.1-70B-Instruct": {
1388-
"max_tokens": 128000,
1387+
"max_tokens": 2048,
13891388
"max_input_tokens": 128000,
1390-
"max_output_tokens": 128000,
1389+
"max_output_tokens": 2048,
13911390
"input_cost_per_token": 0.00000268,
13921391
"output_cost_per_token": 0.00000354,
13931392
"litellm_provider": "azure_ai",
13941393
"mode": "chat",
13951394
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice"
13961395
},
13971396
"azure_ai/Meta-Llama-3.1-405B-Instruct": {
1398-
"max_tokens": 128000,
1397+
"max_tokens": 2048,
13991398
"max_input_tokens": 128000,
1400-
"max_output_tokens": 128000,
1399+
"max_output_tokens": 2048,
14011400
"input_cost_per_token": 0.00000533,
14021401
"output_cost_per_token": 0.000016,
14031402
"litellm_provider": "azure_ai",
14041403
"mode": "chat",
14051404
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice"
14061405
},
14071406
"azure_ai/Phi-3.5-mini-instruct": {
1408-
"max_tokens": 128000,
1407+
"max_tokens": 4096,
14091408
"max_input_tokens": 128000,
14101409
"max_output_tokens": 4096,
14111410
"input_cost_per_token": 0.00000013,
@@ -1416,7 +1415,7 @@
14161415
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
14171416
},
14181417
"azure_ai/Phi-3.5-vision-instruct": {
1419-
"max_tokens": 128000,
1418+
"max_tokens": 4096,
14201419
"max_input_tokens": 128000,
14211420
"max_output_tokens": 4096,
14221421
"input_cost_per_token": 0.00000013,
@@ -1427,7 +1426,7 @@
14271426
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
14281427
},
14291428
"azure_ai/Phi-3.5-MoE-instruct": {
1430-
"max_tokens": 128000,
1429+
"max_tokens": 4096,
14311430
"max_input_tokens": 128000,
14321431
"max_output_tokens": 4096,
14331432
"input_cost_per_token": 0.00000016,
@@ -1449,7 +1448,7 @@
14491448
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
14501449
},
14511450
"azure_ai/Phi-3-mini-128k-instruct": {
1452-
"max_tokens": 128000,
1451+
"max_tokens": 4096,
14531452
"max_input_tokens": 128000,
14541453
"max_output_tokens": 4096,
14551454
"input_cost_per_token": 0.00000013,
@@ -1460,7 +1459,7 @@
14601459
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
14611460
},
14621461
"azure_ai/Phi-3-small-8k-instruct": {
1463-
"max_tokens": 8192,
1462+
"max_tokens": 4096,
14641463
"max_input_tokens": 8192,
14651464
"max_output_tokens": 4096,
14661465
"input_cost_per_token": 0.00000015,
@@ -1471,7 +1470,7 @@
14711470
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
14721471
},
14731472
"azure_ai/Phi-3-small-128k-instruct": {
1474-
"max_tokens": 128000,
1473+
"max_tokens": 4096,
14751474
"max_input_tokens": 128000,
14761475
"max_output_tokens": 4096,
14771476
"input_cost_per_token": 0.00000015,
@@ -1493,7 +1492,7 @@
14931492
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
14941493
},
14951494
"azure_ai/Phi-3-medium-128k-instruct": {
1496-
"max_tokens": 128000,
1495+
"max_tokens": 4096,
14971496
"max_input_tokens": 128000,
14981497
"max_output_tokens": 4096,
14991498
"input_cost_per_token": 0.00000017,

0 commit comments

Comments
 (0)