Skip to content

new prices #96

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 17, 2025
Merged

new prices #96

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -917,6 +917,12 @@ Units denominated in USD. All prices can be located in `model_prices.json`.
| fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct | $0.1 | $0.1 | 16,384 | 16384 |
| assemblyai/nano | -- | -- | nan | nan |
| assemblyai/best | -- | -- | nan | nan |
| azure/gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,384 | 4096 |
| azure/gpt-3.5-turbo | $0.5 | $1.5 | 4,097 | 4096 |
| gemini-2.0-pro-exp-02-05 | $ 0.00 | $ 0.00 | 2,097,152 | 8192 |
| us.meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | 128,000 | 4096 |
| perplexity/sonar | $ 1.00 | $ 1.00 | 127,072 | 127072 |
| perplexity/sonar-pro | $ 3.00 | $15.00 | 200,000 | 8096 |

### Running locally

Expand Down
8 changes: 7 additions & 1 deletion pricing_table.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -790,4 +790,10 @@
| together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free | $ 0.00 | $ 0.00 | nan | nan |
| fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct | $0.1 | $0.1 | 16,384 | 16384 |
| assemblyai/nano | -- | -- | nan | nan |
| assemblyai/best | -- | -- | nan | nan |
| assemblyai/best | -- | -- | nan | nan |
| azure/gpt-3.5-turbo-0125 | $0.5 | $1.5 | 16,384 | 4096 |
| azure/gpt-3.5-turbo | $0.5 | $1.5 | 4,097 | 4096 |
| gemini-2.0-pro-exp-02-05 | $ 0.00 | $ 0.00 | 2,097,152 | 8192 |
| us.meta.llama3-3-70b-instruct-v1:0 | $0.72 | $0.72 | 128,000 | 4096 |
| perplexity/sonar | $ 1.00 | $ 1.00 | 127,072 | 127072 |
| perplexity/sonar-pro | $ 3.00 | $15.00 | 200,000 | 8096 |
153 changes: 112 additions & 41 deletions tokencost/model_prices.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6455,8 +6455,7 @@
"input_cost_per_token": 3.5e-07,
"output_cost_per_token": 1.4e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/codellama-70b-instruct": {
"max_tokens": 16384,
Expand All @@ -6465,8 +6464,7 @@
"input_cost_per_token": 7e-07,
"output_cost_per_token": 2.8e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/llama-3.1-70b-instruct": {
"max_tokens": 131072,
Expand All @@ -6475,8 +6473,7 @@
"input_cost_per_token": 1e-06,
"output_cost_per_token": 1e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/llama-3.1-8b-instruct": {
"max_tokens": 131072,
Expand All @@ -6485,8 +6482,7 @@
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/llama-3.1-sonar-huge-128k-online": {
"max_tokens": 127072,
Expand All @@ -6496,8 +6492,7 @@
"output_cost_per_token": 5e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"deprecation_date": "2025-02-22",
"supports_tool_choice": true
"deprecation_date": "2025-02-22"
},
"perplexity/llama-3.1-sonar-large-128k-online": {
"max_tokens": 127072,
Expand All @@ -6507,8 +6502,7 @@
"output_cost_per_token": 1e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"deprecation_date": "2025-02-22",
"supports_tool_choice": true
"deprecation_date": "2025-02-22"
},
"perplexity/llama-3.1-sonar-large-128k-chat": {
"max_tokens": 131072,
Expand All @@ -6518,8 +6512,7 @@
"output_cost_per_token": 1e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"deprecation_date": "2025-02-22",
"supports_tool_choice": true
"deprecation_date": "2025-02-22"
},
"perplexity/llama-3.1-sonar-small-128k-chat": {
"max_tokens": 131072,
Expand All @@ -6529,8 +6522,7 @@
"output_cost_per_token": 2e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"deprecation_date": "2025-02-22",
"supports_tool_choice": true
"deprecation_date": "2025-02-22"
},
"perplexity/llama-3.1-sonar-small-128k-online": {
"max_tokens": 127072,
Expand All @@ -6540,8 +6532,7 @@
"output_cost_per_token": 2e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"deprecation_date": "2025-02-22",
"supports_tool_choice": true
"deprecation_date": "2025-02-22"
},
"perplexity/pplx-7b-chat": {
"max_tokens": 8192,
Expand All @@ -6550,8 +6541,7 @@
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2.8e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/pplx-70b-chat": {
"max_tokens": 4096,
Expand All @@ -6560,8 +6550,7 @@
"input_cost_per_token": 7e-07,
"output_cost_per_token": 2.8e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/pplx-7b-online": {
"max_tokens": 4096,
Expand All @@ -6571,8 +6560,7 @@
"output_cost_per_token": 2.8e-07,
"input_cost_per_request": 0.005,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/pplx-70b-online": {
"max_tokens": 4096,
Expand All @@ -6582,8 +6570,7 @@
"output_cost_per_token": 2.8e-06,
"input_cost_per_request": 0.005,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/llama-2-70b-chat": {
"max_tokens": 4096,
Expand All @@ -6592,8 +6579,7 @@
"input_cost_per_token": 7e-07,
"output_cost_per_token": 2.8e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/mistral-7b-instruct": {
"max_tokens": 4096,
Expand All @@ -6602,8 +6588,7 @@
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2.8e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/mixtral-8x7b-instruct": {
"max_tokens": 4096,
Expand All @@ -6612,8 +6597,7 @@
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2.8e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/sonar-small-chat": {
"max_tokens": 16384,
Expand All @@ -6622,8 +6606,7 @@
"input_cost_per_token": 7e-08,
"output_cost_per_token": 2.8e-07,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/sonar-small-online": {
"max_tokens": 12000,
Expand All @@ -6633,8 +6616,7 @@
"output_cost_per_token": 2.8e-07,
"input_cost_per_request": 0.005,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/sonar-medium-chat": {
"max_tokens": 16384,
Expand All @@ -6643,8 +6625,7 @@
"input_cost_per_token": 6e-07,
"output_cost_per_token": 1.8e-06,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"perplexity/sonar-medium-online": {
"max_tokens": 12000,
Expand All @@ -6654,8 +6635,7 @@
"output_cost_per_token": 1.8e-06,
"input_cost_per_request": 0.005,
"litellm_provider": "perplexity",
"mode": "chat",
"supports_tool_choice": true
"mode": "chat"
},
"fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": {
"max_tokens": 16384,
Expand Down Expand Up @@ -8429,7 +8409,9 @@
"input_cost_per_token": 7.2e-07,
"output_cost_per_token": 7.2e-07,
"litellm_provider": "bedrock_converse",
"mode": "chat"
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": false
},
"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": {
"input_cost_per_token": 1.8e-07,
Expand Down Expand Up @@ -9194,5 +9176,94 @@
"input_cost_per_second": 3.333e-05,
"output_cost_per_second": 0.0,
"litellm_provider": "assemblyai"
},
"azure/gpt-3.5-turbo-0125": {
"max_tokens": 4096,
"max_input_tokens": 16384,
"max_output_tokens": 4096,
"input_cost_per_token": 5e-07,
"output_cost_per_token": 1.5e-06,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"deprecation_date": "2025-03-31",
"supports_tool_choice": true
},
"azure/gpt-3.5-turbo": {
"max_tokens": 4096,
"max_input_tokens": 4097,
"max_output_tokens": 4096,
"input_cost_per_token": 5e-07,
"output_cost_per_token": 1.5e-06,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true
},
"gemini-2.0-pro-exp-02-05": {
"max_tokens": 8192,
"max_input_tokens": 2097152,
"max_output_tokens": 8192,
"max_images_per_prompt": 3000,
"max_videos_per_prompt": 10,
"max_video_length": 1,
"max_audio_length_hours": 8.4,
"max_audio_per_prompt": 1,
"max_pdf_size_mb": 30,
"input_cost_per_image": 0,
"input_cost_per_video_per_second": 0,
"input_cost_per_audio_per_second": 0,
"input_cost_per_token": 0,
"input_cost_per_character": 0,
"input_cost_per_token_above_128k_tokens": 0,
"input_cost_per_character_above_128k_tokens": 0,
"input_cost_per_image_above_128k_tokens": 0,
"input_cost_per_video_per_second_above_128k_tokens": 0,
"input_cost_per_audio_per_second_above_128k_tokens": 0,
"output_cost_per_token": 0,
"output_cost_per_character": 0,
"output_cost_per_token_above_128k_tokens": 0,
"output_cost_per_character_above_128k_tokens": 0,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_system_messages": true,
"supports_function_calling": true,
"supports_vision": true,
"supports_audio_input": true,
"supports_video_input": true,
"supports_pdf_input": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"us.meta.llama3-3-70b-instruct-v1:0": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 7.2e-07,
"output_cost_per_token": 7.2e-07,
"litellm_provider": "bedrock_converse",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": false
},
"perplexity/sonar": {
"max_tokens": 127072,
"max_input_tokens": 127072,
"max_output_tokens": 127072,
"input_cost_per_token": 1e-06,
"output_cost_per_token": 1e-06,
"litellm_provider": "perplexity",
"mode": "chat"
},
"perplexity/sonar-pro": {
"max_tokens": 200000,
"max_input_tokens": 200000,
"max_output_tokens": 8096,
"input_cost_per_token": 3e-06,
"output_cost_per_token": 1.5e-05,
"litellm_provider": "perplexity",
"mode": "chat"
}
}