tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-02 04:21:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

doc fix

Browse Source
This commit is contained in:
Ishaan Jaff
2025-01-31 21:19:39 -08:00
parent b8445436cd
commit 1d9ccb7fbe
2 changed files with 25 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/providers/bedrock.md
-59
View File
@@ -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:
<Tabs>
<TabItem value="sdk" label="SDK">
```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"}]
)
```
</TabItem>
<TabItem value="proxy" label="PROXY">
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?"
}
]
}'
```
</TabItem>
</Tabs>
## Bedrock Embedding
### API keys
litellm/model_prices_and_context_window_backup.json
+25 -8
View File
@@ -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,