Skip to content

Commit bd79079

Browse files
areibmanareibman
committed
new prices
1 parent 54ef6ba commit bd79079

File tree

3 files changed

+125
-42
lines changed

3 files changed

+125
-42
lines changed

‎README.md‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -917,6 +917,12 @@ Units denominated in USD. All prices can be located in `model_prices.json`.
917917
| fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct | $0.1 | $0.1 | 16,384 | 16384 |
918918
| assemblyai/nano | -- | -- | nan | nan |
919919
| assemblyai/best | -- | -- | nan | nan |
920+
| azure/gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,384 | 4096 |
921+
| azure/gpt-3.5-turbo | $0.5 | $1.5 | 4,097 | 4096 |
922+
| gemini-2.0-pro-exp-02-05 | $ 0.00 | $ 0.00 | 2,097,152 | 8192 |
923+
| us.meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | 128,000 | 4096 |
924+
| perplexity/sonar | $ 1.00 | $ 1.00 | 127,072 | 127072 |
925+
| perplexity/sonar-pro | $ 3.00 | $15.00 | 200,000 | 8096 |
920926

921927
### Running locally
922928

‎pricing_table.md‎

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -790,4 +790,10 @@
790790
| together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free | $ 0.00 | $ 0.00 | nan | nan |
791791
| fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct | $0.1 | $0.1 | 16,384 | 16384 |
792792
| assemblyai/nano | -- | -- | nan | nan |
793-
| assemblyai/best | -- | -- | nan | nan |
793+
| assemblyai/best | -- | -- | nan | nan |
794+
| azure/gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,384 | 4096 |
795+
| azure/gpt-3.5-turbo | $0.5 | $1.5 | 4,097 | 4096 |
796+
| gemini-2.0-pro-exp-02-05 | $ 0.00 | $ 0.00 | 2,097,152 | 8192 |
797+
| us.meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | 128,000 | 4096 |
798+
| perplexity/sonar | $ 1.00 | $ 1.00 | 127,072 | 127072 |
799+
| perplexity/sonar-pro | $ 3.00 | $15.00 | 200,000 | 8096 |

‎tokencost/model_prices.json‎

Lines changed: 112 additions & 41 deletions
Original file line numberDiff line numberDiff line change
@@ -6455,8 +6455,7 @@
64556455
"input_cost_per_token": 3.5e-07,
64566456
"output_cost_per_token": 1.4e-06,
64576457
"litellm_provider": "perplexity",
6458-
"mode": "chat",
6459-
"supports_tool_choice": true
6458+
"mode": "chat"
64606459
},
64616460
"perplexity/codellama-70b-instruct": {
64626461
"max_tokens": 16384,
@@ -6465,8 +6464,7 @@
64656464
"input_cost_per_token": 7e-07,
64666465
"output_cost_per_token": 2.8e-06,
64676466
"litellm_provider": "perplexity",
6468-
"mode": "chat",
6469-
"supports_tool_choice": true
6467+
"mode": "chat"
64706468
},
64716469
"perplexity/llama-3.1-70b-instruct": {
64726470
"max_tokens": 131072,
@@ -6475,8 +6473,7 @@
64756473
"input_cost_per_token": 1e-06,
64766474
"output_cost_per_token": 1e-06,
64776475
"litellm_provider": "perplexity",
6478-
"mode": "chat",
6479-
"supports_tool_choice": true
6476+
"mode": "chat"
64806477
},
64816478
"perplexity/llama-3.1-8b-instruct": {
64826479
"max_tokens": 131072,
@@ -6485,8 +6482,7 @@
64856482
"input_cost_per_token": 2e-07,
64866483
"output_cost_per_token": 2e-07,
64876484
"litellm_provider": "perplexity",
6488-
"mode": "chat",
6489-
"supports_tool_choice": true
6485+
"mode": "chat"
64906486
},
64916487
"perplexity/llama-3.1-sonar-huge-128k-online": {
64926488
"max_tokens": 127072,
@@ -6496,8 +6492,7 @@
64966492
"output_cost_per_token": 5e-06,
64976493
"litellm_provider": "perplexity",
64986494
"mode": "chat",
6499-
"deprecation_date": "2025-02-22",
6500-
"supports_tool_choice": true
6495+
"deprecation_date": "2025-02-22"
65016496
},
65026497
"perplexity/llama-3.1-sonar-large-128k-online": {
65036498
"max_tokens": 127072,
@@ -6507,8 +6502,7 @@
65076502
"output_cost_per_token": 1e-06,
65086503
"litellm_provider": "perplexity",
65096504
"mode": "chat",
6510-
"deprecation_date": "2025-02-22",
6511-
"supports_tool_choice": true
6505+
"deprecation_date": "2025-02-22"
65126506
},
65136507
"perplexity/llama-3.1-sonar-large-128k-chat": {
65146508
"max_tokens": 131072,
@@ -6518,8 +6512,7 @@
65186512
"output_cost_per_token": 1e-06,
65196513
"litellm_provider": "perplexity",
65206514
"mode": "chat",
6521-
"deprecation_date": "2025-02-22",
6522-
"supports_tool_choice": true
6515+
"deprecation_date": "2025-02-22"
65236516
},
65246517
"perplexity/llama-3.1-sonar-small-128k-chat": {
65256518
"max_tokens": 131072,
@@ -6529,8 +6522,7 @@
65296522
"output_cost_per_token": 2e-07,
65306523
"litellm_provider": "perplexity",
65316524
"mode": "chat",
6532-
"deprecation_date": "2025-02-22",
6533-
"supports_tool_choice": true
6525+
"deprecation_date": "2025-02-22"
65346526
},
65356527
"perplexity/llama-3.1-sonar-small-128k-online": {
65366528
"max_tokens": 127072,
@@ -6540,8 +6532,7 @@
65406532
"output_cost_per_token": 2e-07,
65416533
"litellm_provider": "perplexity",
65426534
"mode": "chat",
6543-
"deprecation_date": "2025-02-22",
6544-
"supports_tool_choice": true
6535+
"deprecation_date": "2025-02-22"
65456536
},
65466537
"perplexity/pplx-7b-chat": {
65476538
"max_tokens": 8192,
@@ -6550,8 +6541,7 @@
65506541
"input_cost_per_token": 7e-08,
65516542
"output_cost_per_token": 2.8e-07,
65526543
"litellm_provider": "perplexity",
6553-
"mode": "chat",
6554-
"supports_tool_choice": true
6544+
"mode": "chat"
65556545
},
65566546
"perplexity/pplx-70b-chat": {
65576547
"max_tokens": 4096,
@@ -6560,8 +6550,7 @@
65606550
"input_cost_per_token": 7e-07,
65616551
"output_cost_per_token": 2.8e-06,
65626552
"litellm_provider": "perplexity",
6563-
"mode": "chat",
6564-
"supports_tool_choice": true
6553+
"mode": "chat"
65656554
},
65666555
"perplexity/pplx-7b-online": {
65676556
"max_tokens": 4096,
@@ -6571,8 +6560,7 @@
65716560
"output_cost_per_token": 2.8e-07,
65726561
"input_cost_per_request": 0.005,
65736562
"litellm_provider": "perplexity",
6574-
"mode": "chat",
6575-
"supports_tool_choice": true
6563+
"mode": "chat"
65766564
},
65776565
"perplexity/pplx-70b-online": {
65786566
"max_tokens": 4096,
@@ -6582,8 +6570,7 @@
65826570
"output_cost_per_token": 2.8e-06,
65836571
"input_cost_per_request": 0.005,
65846572
"litellm_provider": "perplexity",
6585-
"mode": "chat",
6586-
"supports_tool_choice": true
6573+
"mode": "chat"
65876574
},
65886575
"perplexity/llama-2-70b-chat": {
65896576
"max_tokens": 4096,
@@ -6592,8 +6579,7 @@
65926579
"input_cost_per_token": 7e-07,
65936580
"output_cost_per_token": 2.8e-06,
65946581
"litellm_provider": "perplexity",
6595-
"mode": "chat",
6596-
"supports_tool_choice": true
6582+
"mode": "chat"
65976583
},
65986584
"perplexity/mistral-7b-instruct": {
65996585
"max_tokens": 4096,
@@ -6602,8 +6588,7 @@
66026588
"input_cost_per_token": 7e-08,
66036589
"output_cost_per_token": 2.8e-07,
66046590
"litellm_provider": "perplexity",
6605-
"mode": "chat",
6606-
"supports_tool_choice": true
6591+
"mode": "chat"
66076592
},
66086593
"perplexity/mixtral-8x7b-instruct": {
66096594
"max_tokens": 4096,
@@ -6612,8 +6597,7 @@
66126597
"input_cost_per_token": 7e-08,
66136598
"output_cost_per_token": 2.8e-07,
66146599
"litellm_provider": "perplexity",
6615-
"mode": "chat",
6616-
"supports_tool_choice": true
6600+
"mode": "chat"
66176601
},
66186602
"perplexity/sonar-small-chat": {
66196603
"max_tokens": 16384,
@@ -6622,8 +6606,7 @@
66226606
"input_cost_per_token": 7e-08,
66236607
"output_cost_per_token": 2.8e-07,
66246608
"litellm_provider": "perplexity",
6625-
"mode": "chat",
6626-
"supports_tool_choice": true
6609+
"mode": "chat"
66276610
},
66286611
"perplexity/sonar-small-online": {
66296612
"max_tokens": 12000,
@@ -6633,8 +6616,7 @@
66336616
"output_cost_per_token": 2.8e-07,
66346617
"input_cost_per_request": 0.005,
66356618
"litellm_provider": "perplexity",
6636-
"mode": "chat",
6637-
"supports_tool_choice": true
6619+
"mode": "chat"
66386620
},
66396621
"perplexity/sonar-medium-chat": {
66406622
"max_tokens": 16384,
@@ -6643,8 +6625,7 @@
66436625
"input_cost_per_token": 6e-07,
66446626
"output_cost_per_token": 1.8e-06,
66456627
"litellm_provider": "perplexity",
6646-
"mode": "chat",
6647-
"supports_tool_choice": true
6628+
"mode": "chat"
66486629
},
66496630
"perplexity/sonar-medium-online": {
66506631
"max_tokens": 12000,
@@ -6654,8 +6635,7 @@
66546635
"output_cost_per_token": 1.8e-06,
66556636
"input_cost_per_request": 0.005,
66566637
"litellm_provider": "perplexity",
6657-
"mode": "chat",
6658-
"supports_tool_choice": true
6638+
"mode": "chat"
66596639
},
66606640
"fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": {
66616641
"max_tokens": 16384,
@@ -8429,7 +8409,9 @@
84298409
"input_cost_per_token": 7.2e-07,
84308410
"output_cost_per_token": 7.2e-07,
84318411
"litellm_provider": "bedrock_converse",
8432-
"mode": "chat"
8412+
"mode": "chat",
8413+
"supports_function_calling": true,
8414+
"supports_tool_choice": false
84338415
},
84348416
"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
84358417
"input_cost_per_token": 1.8e-07,
@@ -9194,5 +9176,94 @@
91949176
"input_cost_per_second": 3.333e-05,
91959177
"output_cost_per_second": 0.0,
91969178
"litellm_provider": "assemblyai"
9179+
},
9180+
"azure/gpt-3.5-turbo-0125": {
9181+
"max_tokens": 4096,
9182+
"max_input_tokens": 16384,
9183+
"max_output_tokens": 4096,
9184+
"input_cost_per_token": 5e-07,
9185+
"output_cost_per_token": 1.5e-06,
9186+
"litellm_provider": "azure",
9187+
"mode": "chat",
9188+
"supports_function_calling": true,
9189+
"supports_parallel_function_calling": true,
9190+
"deprecation_date": "2025-03-31",
9191+
"supports_tool_choice": true
9192+
},
9193+
"azure/gpt-3.5-turbo": {
9194+
"max_tokens": 4096,
9195+
"max_input_tokens": 4097,
9196+
"max_output_tokens": 4096,
9197+
"input_cost_per_token": 5e-07,
9198+
"output_cost_per_token": 1.5e-06,
9199+
"litellm_provider": "azure",
9200+
"mode": "chat",
9201+
"supports_function_calling": true,
9202+
"supports_tool_choice": true
9203+
},
9204+
"gemini-2.0-pro-exp-02-05": {
9205+
"max_tokens": 8192,
9206+
"max_input_tokens": 2097152,
9207+
"max_output_tokens": 8192,
9208+
"max_images_per_prompt": 3000,
9209+
"max_videos_per_prompt": 10,
9210+
"max_video_length": 1,
9211+
"max_audio_length_hours": 8.4,
9212+
"max_audio_per_prompt": 1,
9213+
"max_pdf_size_mb": 30,
9214+
"input_cost_per_image": 0,
9215+
"input_cost_per_video_per_second": 0,
9216+
"input_cost_per_audio_per_second": 0,
9217+
"input_cost_per_token": 0,
9218+
"input_cost_per_character": 0,
9219+
"input_cost_per_token_above_128k_tokens": 0,
9220+
"input_cost_per_character_above_128k_tokens": 0,
9221+
"input_cost_per_image_above_128k_tokens": 0,
9222+
"input_cost_per_video_per_second_above_128k_tokens": 0,
9223+
"input_cost_per_audio_per_second_above_128k_tokens": 0,
9224+
"output_cost_per_token": 0,
9225+
"output_cost_per_character": 0,
9226+
"output_cost_per_token_above_128k_tokens": 0,
9227+
"output_cost_per_character_above_128k_tokens": 0,
9228+
"litellm_provider": "vertex_ai-language-models",
9229+
"mode": "chat",
9230+
"supports_system_messages": true,
9231+
"supports_function_calling": true,
9232+
"supports_vision": true,
9233+
"supports_audio_input": true,
9234+
"supports_video_input": true,
9235+
"supports_pdf_input": true,
9236+
"supports_response_schema": true,
9237+
"supports_tool_choice": true,
9238+
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
9239+
},
9240+
"us.meta.llama3-3-70b-instruct-v1:0": {
9241+
"max_tokens": 4096,
9242+
"max_input_tokens": 128000,
9243+
"max_output_tokens": 4096,
9244+
"input_cost_per_token": 7.2e-07,
9245+
"output_cost_per_token": 7.2e-07,
9246+
"litellm_provider": "bedrock_converse",
9247+
"mode": "chat",
9248+
"supports_function_calling": true,
9249+
"supports_tool_choice": false
9250+
},
9251+
"perplexity/sonar": {
9252+
"max_tokens": 127072,
9253+
"max_input_tokens": 127072,
9254+
"max_output_tokens": 127072,
9255+
"input_cost_per_token": 1e-06,
9256+
"output_cost_per_token": 1e-06,
9257+
"litellm_provider": "perplexity",
9258+
"mode": "chat"
9259+
},
9260+
"perplexity/sonar-pro": {
9261+
"max_tokens": 200000,
9262+
"max_input_tokens": 200000,
9263+
"max_output_tokens": 8096,
9264+
"input_cost_per_token": 3e-06,
9265+
"output_cost_per_token": 1.5e-05,
9266+
"litellm_provider": "perplexity",
9267+
"mode": "chat"
91979268
}
91989269
}

0 commit comments

Comments
 (0)