From 7b6a00d3df82352ae1cdb76f6e7a5c6ac632b7e6 Mon Sep 17 00:00:00 2001 From: Chesars Date: Tue, 16 Dec 2025 13:06:33 -0300 Subject: [PATCH] fix: remove deprecated Groq models and update model registry - Remove 20 deprecated/unavailable Groq models from registry - Add groq/meta-llama/llama-guard-4-12b (new safety model) - Add supports_vision to Llama 4 models (maverick, scout) - Update Groq documentation with current model list - Clean up test file references to deprecated models Fixes #18043 --- docs/my-website/docs/providers/groq.md | 31 +-- ...odel_prices_and_context_window_backup.json | 240 +----------------- model_prices_and_context_window.json | 240 +----------------- tests/test_litellm/test_utils.py | 2 - 4 files changed, 24 insertions(+), 489 deletions(-) diff --git a/docs/my-website/docs/providers/groq.md b/docs/my-website/docs/providers/groq.md index ebed31f720f..55c222635d2 100644 --- a/docs/my-website/docs/providers/groq.md +++ b/docs/my-website/docs/providers/groq.md @@ -150,15 +150,15 @@ We support ALL Groq models, just set `groq/` as a prefix when sending completion | Model Name | Usage | |--------------------|---------------------------------------------------------| -| llama-3.1-8b-instant | `completion(model="groq/llama-3.1-8b-instant", messages)` | -| llama-3.1-70b-versatile | `completion(model="groq/llama-3.1-70b-versatile", messages)` | -| llama3-8b-8192 | `completion(model="groq/llama3-8b-8192", messages)` | -| llama3-70b-8192 | `completion(model="groq/llama3-70b-8192", messages)` | -| llama2-70b-4096 | `completion(model="groq/llama2-70b-4096", messages)` | -| mixtral-8x7b-32768 | `completion(model="groq/mixtral-8x7b-32768", messages)` | -| gemma-7b-it | `completion(model="groq/gemma-7b-it", messages)` | -| moonshotai/kimi-k2-instruct | `completion(model="groq/moonshotai/kimi-k2-instruct", messages)` | -| qwen3-32b | `completion(model="groq/qwen/qwen3-32b", messages)` | +| llama-3.3-70b-versatile | `completion(model="groq/llama-3.3-70b-versatile", messages)` | +| llama-3.1-8b-instant | `completion(model="groq/llama-3.1-8b-instant", messages)` | +| meta-llama/llama-4-scout-17b-16e-instruct | `completion(model="groq/meta-llama/llama-4-scout-17b-16e-instruct", messages)` | +| meta-llama/llama-4-maverick-17b-128e-instruct | `completion(model="groq/meta-llama/llama-4-maverick-17b-128e-instruct", messages)` | +| meta-llama/llama-guard-4-12b | `completion(model="groq/meta-llama/llama-guard-4-12b", messages)` | +| qwen/qwen3-32b | `completion(model="groq/qwen/qwen3-32b", messages)` | +| moonshotai/kimi-k2-instruct-0905 | `completion(model="groq/moonshotai/kimi-k2-instruct-0905", messages)` | +| openai/gpt-oss-120b | `completion(model="groq/openai/gpt-oss-120b", messages)` | +| openai/gpt-oss-20b | `completion(model="groq/openai/gpt-oss-20b", messages)` | ## Groq - Tool / Function Calling Example @@ -261,31 +261,28 @@ if tool_calls: print("second response\n", second_response) ``` -## Groq - Vision Example +## Groq - Vision Example -Select Groq models support vision. Check out their [model list](https://console.groq.com/docs/vision) for more details. +Groq's Llama 4 models support vision. Check out their [model list](https://console.groq.com/docs/vision) for more details. ```python -from litellm import completion - -import os +import os from litellm import completion os.environ["GROQ_API_KEY"] = "your-api-key" -# openai call response = completion( - model = "groq/llama-3.2-11b-vision-preview", + model = "groq/meta-llama/llama-4-scout-17b-16e-instruct", messages=[ { "role": "user", "content": [ { "type": "text", - "text": "What’s in this image?" + "text": "What's in this image?" }, { "type": "image_url", diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2af548ce07e..5754899846c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -17509,75 +17509,6 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "groq", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/distil-whisper-large-v3-en": { - "input_cost_per_second": 5.56e-06, - "litellm_provider": "groq", - "mode": "audio_transcription", - "output_cost_per_second": 0.0 - }, - "groq/gemma-7b-it": { - "deprecation_date": "2024-12-18", - "input_cost_per_token": 7e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 7e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/gemma2-9b-it": { - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07, - "supports_function_calling": false, - "supports_response_schema": false, - "supports_tool_choice": false - }, - "groq/llama-3.1-405b-reasoning": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.1-70b-versatile": { - "deprecation_date": "2025-01-24", - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/llama-3.1-8b-instant": { "input_cost_per_token": 5e-08, "litellm_provider": "groq", @@ -17590,97 +17521,6 @@ "supports_response_schema": false, "supports_tool_choice": true }, - "groq/llama-3.2-11b-text-preview": { - "deprecation_date": "2024-10-28", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-11b-vision-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/llama-3.2-1b-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 4e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-3b-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 6e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-90b-text-preview": { - "deprecation_date": "2024-11-25", - "input_cost_per_token": 9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-90b-vision-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/llama-3.3-70b-specdec": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_tool_choice": true - }, "groq/llama-3.3-70b-versatile": { "input_cost_per_token": 5.9e-07, "litellm_provider": "groq", @@ -17693,7 +17533,7 @@ "supports_response_schema": false, "supports_tool_choice": true }, - "groq/llama-guard-3-8b": { + "groq/meta-llama/llama-guard-4-12b": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 8192, @@ -17702,44 +17542,6 @@ "mode": "chat", "output_cost_per_token": 2e-07 }, - "groq/llama2-70b-4096": { - "input_cost_per_token": 7e-07, - "litellm_provider": "groq", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 8e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama3-groq-70b-8192-tool-use-preview": { - "deprecation_date": "2025-01-06", - "input_cost_per_token": 8.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama3-groq-8b-8192-tool-use-preview": { - "deprecation_date": "2025-01-06", - "input_cost_per_token": 1.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", @@ -17750,7 +17552,8 @@ "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "groq/meta-llama/llama-4-scout-17b-16e-instruct": { "input_cost_per_token": 1.1e-07, @@ -17762,41 +17565,8 @@ "output_cost_per_token": 3.4e-07, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/mistral-saba-24b": { - "input_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.9e-07 - }, - "groq/mixtral-8x7b-32768": { - "deprecation_date": "2025-03-20", - "input_cost_per_token": 2.4e-07, - "litellm_provider": "groq", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2.4e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/moonshotai/kimi-k2-instruct": { - "input_cost_per_token": 1e-06, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-06, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "groq/moonshotai/kimi-k2-instruct-0905": { "input_cost_per_token": 1e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2af548ce07e..5754899846c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -17509,75 +17509,6 @@ "supports_response_schema": true, "supports_vision": true }, - "groq/deepseek-r1-distill-llama-70b": { - "input_cost_per_token": 7.5e-07, - "litellm_provider": "groq", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_function_calling": true, - "supports_reasoning": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/distil-whisper-large-v3-en": { - "input_cost_per_second": 5.56e-06, - "litellm_provider": "groq", - "mode": "audio_transcription", - "output_cost_per_second": 0.0 - }, - "groq/gemma-7b-it": { - "deprecation_date": "2024-12-18", - "input_cost_per_token": 7e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 7e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/gemma2-9b-it": { - "input_cost_per_token": 2e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 2e-07, - "supports_function_calling": false, - "supports_response_schema": false, - "supports_tool_choice": false - }, - "groq/llama-3.1-405b-reasoning": { - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.1-70b-versatile": { - "deprecation_date": "2025-01-24", - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 7.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/llama-3.1-8b-instant": { "input_cost_per_token": 5e-08, "litellm_provider": "groq", @@ -17590,97 +17521,6 @@ "supports_response_schema": false, "supports_tool_choice": true }, - "groq/llama-3.2-11b-text-preview": { - "deprecation_date": "2024-10-28", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-11b-vision-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 1.8e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.8e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/llama-3.2-1b-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 4e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 4e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-3b-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 6e-08, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 6e-08, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-90b-text-preview": { - "deprecation_date": "2024-11-25", - "input_cost_per_token": 9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama-3.2-90b-vision-preview": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true, - "supports_vision": true - }, - "groq/llama-3.3-70b-specdec": { - "deprecation_date": "2025-04-14", - "input_cost_per_token": 5.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 9.9e-07, - "supports_tool_choice": true - }, "groq/llama-3.3-70b-versatile": { "input_cost_per_token": 5.9e-07, "litellm_provider": "groq", @@ -17693,7 +17533,7 @@ "supports_response_schema": false, "supports_tool_choice": true }, - "groq/llama-guard-3-8b": { + "groq/meta-llama/llama-guard-4-12b": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", "max_input_tokens": 8192, @@ -17702,44 +17542,6 @@ "mode": "chat", "output_cost_per_token": 2e-07 }, - "groq/llama2-70b-4096": { - "input_cost_per_token": 7e-07, - "litellm_provider": "groq", - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "max_tokens": 4096, - "mode": "chat", - "output_cost_per_token": 8e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama3-groq-70b-8192-tool-use-preview": { - "deprecation_date": "2025-01-06", - "input_cost_per_token": 8.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 8.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/llama3-groq-8b-8192-tool-use-preview": { - "deprecation_date": "2025-01-06", - "input_cost_per_token": 1.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 8192, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "output_cost_per_token": 1.9e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, "groq/meta-llama/llama-4-maverick-17b-128e-instruct": { "input_cost_per_token": 2e-07, "litellm_provider": "groq", @@ -17750,7 +17552,8 @@ "output_cost_per_token": 6e-07, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "groq/meta-llama/llama-4-scout-17b-16e-instruct": { "input_cost_per_token": 1.1e-07, @@ -17762,41 +17565,8 @@ "output_cost_per_token": 3.4e-07, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true - }, - "groq/mistral-saba-24b": { - "input_cost_per_token": 7.9e-07, - "litellm_provider": "groq", - "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, - "mode": "chat", - "output_cost_per_token": 7.9e-07 - }, - "groq/mixtral-8x7b-32768": { - "deprecation_date": "2025-03-20", - "input_cost_per_token": 2.4e-07, - "litellm_provider": "groq", - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "chat", - "output_cost_per_token": 2.4e-07, - "supports_function_calling": true, - "supports_response_schema": false, - "supports_tool_choice": true - }, - "groq/moonshotai/kimi-k2-instruct": { - "input_cost_per_token": 1e-06, - "litellm_provider": "groq", - "max_input_tokens": 131072, - "max_output_tokens": 16384, - "max_tokens": 131072, - "mode": "chat", - "output_cost_per_token": 3e-06, - "supports_function_calling": true, - "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "groq/moonshotai/kimi-k2-instruct-0905": { "input_cost_per_token": 1e-06, diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 2bd94488ba2..a3dc6f5085d 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -870,8 +870,6 @@ SKIP_MODELS = [ "jamba", "deepinfra", "mistral.", - "groq/llama-guard-3-8b", - "groq/gemma2-9b-it", ] # Bedrock models to block - organized by type