From 1d9ccb7fbee41a9bf0742e6a1f04fa070adf388b Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Fri, 31 Jan 2025 21:19:39 -0800 Subject: [PATCH] doc fix --- docs/my-website/docs/providers/bedrock.md | 59 ------------------- ...odel_prices_and_context_window_backup.json | 33 ++++++++--- 2 files changed, 25 insertions(+), 67 deletions(-) diff --git a/docs/my-website/docs/providers/bedrock.md b/docs/my-website/docs/providers/bedrock.md index 4b85b55533..ad2124676f 100644 --- a/docs/my-website/docs/providers/bedrock.md +++ b/docs/my-website/docs/providers/bedrock.md @@ -1399,65 +1399,6 @@ Here's an example of using a bedrock model with LiteLLM. For a complete list, re | Mistral 7B Instruct | `completion(model='bedrock/mistral.mistral-7b-instruct-v0:2', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | | Mixtral 8x7B Instruct | `completion(model='bedrock/mistral.mixtral-8x7b-instruct-v0:1', messages=messages)` | `os.environ['AWS_ACCESS_KEY_ID']`, `os.environ['AWS_SECRET_ACCESS_KEY']`, `os.environ['AWS_REGION_NAME']` | -### Deepseek - -Native Deepseek support will be [available soon](https://github.com/BerriAI/litellm/pull/8132) - -Till then, use this: - - - - -```python -import litellm -response = litellm.completion( - model="bedrock/meta.DeepSeek-R1-Distill-Llama-8B", - model_id="provisioned-model-arn", - messages=[{"content": "Hello, how are you?", "role": "user"}] -) -``` - - - - -1. Setup config.yaml - -```yaml -model_list: - - model_name: bedrock-deepseek - litellm_params: - model: bedrock/meta.DeepSeek-R1-Distill-Llama-8B - model_id: provisioned-model-arn -``` - -2. Start proxy server - -```bash -litellm --config config.yaml - -# RUNNING on http://0.0.0.0:4000 -``` - -3. Test it! - -```bash -curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \ --H 'Content-Type: application/json' \ --H 'Authorization: Bearer sk-1234' \ --d '{ - "model": "bedrock-deepseek", - "messages": [ - { - "role": "user", - "content": "What'\''s the weather like in Boston today 236589?" - } - ] -}' -``` - - - - ## Bedrock Embedding ### API keys diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 80c70fc58f..d23fbed81f 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -915,7 +915,7 @@ }, "whisper-1": { "mode": "audio_transcription", - "input_cost_per_second": 0, + "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "litellm_provider": "openai" }, @@ -941,10 +941,22 @@ }, "azure/whisper-1": { "mode": "audio_transcription", - "input_cost_per_second": 0, + "input_cost_per_second": 0.0001, "output_cost_per_second": 0.0001, "litellm_provider": "azure" }, + "azure/o3-mini": { + "max_tokens": 100000, + "max_input_tokens": 200000, + "max_output_tokens": 100000, + "input_cost_per_token": 0.0000011, + "output_cost_per_token": 0.0000044, + "cache_read_input_token_cost": 0.00000055, + "litellm_provider": "azure", + "mode": "chat", + "supports_vision": true, + "supports_prompt_caching": true + }, "azure/o1-mini": { "max_tokens": 65536, "max_input_tokens": 128000, @@ -1035,6 +1047,7 @@ "max_output_tokens": 16384, "input_cost_per_token": 0.00000275, "output_cost_per_token": 0.000011, + "cache_read_input_token_cost": 0.00000125, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1075,6 +1088,7 @@ "max_output_tokens": 16384, "input_cost_per_token": 0.0000025, "output_cost_per_token": 0.000010, + "cache_read_input_token_cost": 0.00000125, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -3322,8 +3336,9 @@ "max_images_per_prompt": 16, "max_videos_per_prompt": 1, "max_video_length": 2, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015, + "input_cost_per_image": 0.0025, "litellm_provider": "vertex_ai-vision-models", "mode": "chat", "supports_function_calling": true, @@ -3337,8 +3352,9 @@ "max_images_per_prompt": 16, "max_videos_per_prompt": 1, "max_video_length": 2, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015, + "input_cost_per_image": 0.0025, "litellm_provider": "vertex_ai-vision-models", "mode": "chat", "supports_function_calling": true, @@ -3352,8 +3368,9 @@ "max_images_per_prompt": 16, "max_videos_per_prompt": 1, "max_video_length": 2, - "input_cost_per_token": 0.00000025, - "output_cost_per_token": 0.0000005, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015, + "input_cost_per_image": 0.0025, "litellm_provider": "vertex_ai-vision-models", "mode": "chat", "supports_function_calling": true,