Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
14 changes: 10 additions & 4 deletions pricing_table.md
Original file line number Diff line number Diff line change
Expand Up @@ -151,7 +151,7 @@
| groq/llama2-70b-4096 | $0.7 | $0.8 | 4,096 | 4096 |
| groq/llama3-8b-8192 | $0.05 | $0.08 | 8,192 | 8192 |
| groq/llama3-70b-8192 | $0.59 | $0.79 | 8,192 | 8192 |
| groq/llama-3.1-8b-instant | $0.05 | $0.08 | 8,192 | 8192 |
| groq/llama-3.1-8b-instant | $0.05 | $0.08 | 128,000 | 8192 |
| groq/llama-3.1-70b-versatile | $0.59 | $0.79 | 8,192 | 8192 |
| groq/llama-3.1-405b-reasoning | $0.59 | $0.79 | 8,192 | 8192 |
| groq/mixtral-8x7b-32768 | $0.24 | $0.24 | 32,768 | 32768 |
Expand Down Expand Up @@ -714,7 +714,7 @@
| mistral/pixtral-large-2411 | $2 | $6 | 128,000 | 128000 |
| deepseek/deepseek-chat | $0.27 | $1.1 | 65,536 | 8192 |
| deepseek/deepseek-coder | $0.14 | $0.28 | 128,000 | 4096 |
| groq/llama-3.3-70b-versatile | $0.59 | $0.79 | 128,000 | 8192 |
| groq/llama-3.3-70b-versatile | $0.59 | $0.79 | 128,000 | 32768 |
| groq/llama-3.3-70b-specdec | $0.59 | $0.99 | 8,192 | 8192 |
| friendliai/meta-llama-3.1-8b-instruct | $0.1 | $0.1 | 8,192 | 8192 |
| friendliai/meta-llama-3.1-70b-instruct | $0.6 | $0.6 | 8,192 | 8192 |
Expand Down Expand Up @@ -768,7 +768,7 @@
| xai/grok-2-1212 | $2 | $10 | 131,072 | 131072 |
| xai/grok-2 | $2 | $10 | 131,072 | 131072 |
| xai/grok-2-latest | $2 | $10 | 131,072 | 131072 |
| groq/deepseek-r1-distill-llama-70b | $0.75 | $0.99 | 131,072 | 131072 |
| groq/deepseek-r1-distill-llama-70b | $0.75 | $0.99 | 128,000 | 128000 |
| gemini/gemini-2.0-flash | $0.1 | $0.4 | 1,048,576 | 8192 |
| gemini-2.0-flash-001 | $0.15 | $0.6 | 1,048,576 | 8192 |
| gemini-2.0-flash-thinking-exp | $0 | $0 | 1,048,576 | 8192 |
Expand Down Expand Up @@ -1022,4 +1022,10 @@
| nscale/stabilityai/stable-diffusion-xl-base-1.0 | -- | -- | nan | nan |
| azure/gpt-4o-mini-tts | $2.5 | $10 | nan | nan |
| azure_ai/embed-v-4-0 | $0.12 | $0 | 128,000 | nan |
| eu.anthropic.claude-3-7-sonnet-20250219-v1:0 | $3 | $15 | 200,000 | 8192 |
| eu.anthropic.claude-3-7-sonnet-20250219-v1:0 | $3 | $15 | 200,000 | 8192 |
| groq/llama-guard-3-8b | $0.2 | $0.2 | 8,192 | 8192 |
| groq/meta-llama/llama-4-scout-17b-16e-instruct | $0.11 | $0.34 | 131,072 | 8192 |
| groq/meta-llama/llama-4-maverick-17b-128e-instruct | $0.2 | $0.6 | 131,072 | 8192 |
| groq/mistral-saba-24b | $0.79 | $0.79 | 32,000 | 32000 |
| groq/qwen-qwq-32b | $0.29 | $0.39 | 128,000 | 128000 |
| groq/playai-tts | -- | -- | 10,000 | 10000 |
148 changes: 108 additions & 40 deletions tokencost/model_prices.json
Original file line number Diff line number Diff line change
Expand Up @@ -1709,10 +1709,7 @@
"input_cost_per_token": 5e-08,
"output_cost_per_token": 8e-08,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"mode": "chat"
},
"groq/llama3-70b-8192": {
"max_tokens": 8192,
Expand All @@ -1721,14 +1718,11 @@
"input_cost_per_token": 5.9e-07,
"output_cost_per_token": 7.9e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"mode": "chat"
},
"groq/llama-3.1-8b-instant": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"input_cost_per_token": 5e-08,
"output_cost_per_token": 8e-08,
Expand All @@ -1748,7 +1742,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-01-24"
},
"groq/llama-3.1-405b-reasoning": {
"max_tokens": 8192,
Expand All @@ -1772,7 +1767,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-03-20"
},
"groq/gemma-7b-it": {
"max_tokens": 8192,
Expand All @@ -1784,7 +1780,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2024-12-18"
},
"groq/gemma2-9b-it": {
"max_tokens": 8192,
Expand All @@ -1794,9 +1791,9 @@
"output_cost_per_token": 2e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true,
"supports_function_calling": false,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": false
},
"groq/llama3-groq-70b-8192-tool-use-preview": {
"max_tokens": 8192,
Expand All @@ -1808,7 +1805,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-1-6"
},
"groq/llama3-groq-8b-8192-tool-use-preview": {
"max_tokens": 8192,
Expand All @@ -1820,7 +1818,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-1-6"
},
"cerebras/llama3.1-8b": {
"max_tokens": 128000,
Expand Down Expand Up @@ -7701,7 +7700,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-04-14"
},
"groq/llama-3.2-3b-preview": {
"max_tokens": 8192,
Expand All @@ -7713,7 +7713,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-04-14"
},
"groq/llama-3.2-11b-text-preview": {
"max_tokens": 8192,
Expand All @@ -7725,7 +7726,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2024-10-28"
},
"groq/llama-3.2-11b-vision-preview": {
"max_tokens": 8192,
Expand All @@ -7738,7 +7740,8 @@
"supports_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-04-14"
},
"groq/llama-3.2-90b-text-preview": {
"max_tokens": 8192,
Expand All @@ -7750,7 +7753,8 @@
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2024-11-25"
},
"groq/llama-3.2-90b-vision-preview": {
"max_tokens": 8192,
Expand All @@ -7763,7 +7767,8 @@
"supports_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-04-14"
},
"vertex_ai/claude-3-sonnet": {
"max_tokens": 4096,
Expand Down Expand Up @@ -8224,9 +8229,9 @@
"supports_prompt_caching": true
},
"groq/llama-3.3-70b-versatile": {
"max_tokens": 8192,
"max_tokens": 32768,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_output_tokens": 32768,
"input_cost_per_token": 5.9e-07,
"output_cost_per_token": 7.9e-07,
"litellm_provider": "groq",
Expand All @@ -8243,7 +8248,8 @@
"output_cost_per_token": 9.9e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_tool_choice": true
"supports_tool_choice": true,
"deprecation_date": "2025-04-14"
},
"friendliai/meta-llama-3.1-8b-instruct": {
"max_tokens": 8192,
Expand Down Expand Up @@ -8964,17 +8970,16 @@
"supports_tool_choice": true
},
"groq/deepseek-r1-distill-llama-70b": {
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 7.5e-07,
"output_cost_per_token": 9.9e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_system_messages": false,
"supports_function_calling": false,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_response_schema": false,
"supports_tool_choice": true
},
"gemini/gemini-2.0-flash": {
Expand Down Expand Up @@ -11953,22 +11958,22 @@
"source": "https://x.ai/api#pricing"
},
"groq/whisper-large-v3": {
"mode": "audio_transcription",
"input_cost_per_second": 3.083e-05,
"output_cost_per_second": 0,
"litellm_provider": "groq"
"output_cost_per_second": 0.0,
"litellm_provider": "groq",
"mode": "audio_transcription"
},
"groq/whisper-large-v3-turbo": {
"mode": "audio_transcription",
"input_cost_per_second": 1.111e-05,
"output_cost_per_second": 0,
"litellm_provider": "groq"
"output_cost_per_second": 0.0,
"litellm_provider": "groq",
"mode": "audio_transcription"
},
"groq/distil-whisper-large-v3-en": {
"mode": "audio_transcription",
"input_cost_per_second": 5.56e-06,
"output_cost_per_second": 0,
"litellm_provider": "groq"
"output_cost_per_second": 0.0,
"litellm_provider": "groq",
"mode": "audio_transcription"
},
"meta_llama/Llama-4-Scout-17B-16E-Instruct-FP8": {
"max_tokens": 128000,
Expand Down Expand Up @@ -13222,5 +13227,68 @@
"supports_pdf_input": true,
"supports_tool_choice": true,
"supports_reasoning": true
},
"groq/llama-guard-3-8b": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 2e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "groq",
"mode": "chat"
},
"groq/meta-llama/llama-4-scout-17b-16e-instruct": {
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"input_cost_per_token": 1.1e-07,
"output_cost_per_token": 3.4e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"groq/meta-llama/llama-4-maverick-17b-128e-instruct": {
"max_tokens": 8192,
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"input_cost_per_token": 2e-07,
"output_cost_per_token": 6e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"groq/mistral-saba-24b": {
"max_tokens": 32000,
"max_input_tokens": 32000,
"max_output_tokens": 32000,
"input_cost_per_token": 7.9e-07,
"output_cost_per_token": 7.9e-07,
"litellm_provider": "groq",
"mode": "chat"
},
"groq/qwen-qwq-32b": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 2.9e-07,
"output_cost_per_token": 3.9e-07,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"groq/playai-tts": {
"max_tokens": 10000,
"max_input_tokens": 10000,
"max_output_tokens": 10000,
"input_cost_per_character": 5e-05,
"litellm_provider": "groq",
"mode": "audio_speech"
}
}