scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

docs stable release

Browse source
This commit is contained in:
Ishaan Jaff 2025-07-10 14:53:29 -07:00
parent 6fa0da6ae2
commit 610d56ae5d
2 changed files with 52 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
docs/my-website/release_notes/v1.74.0-stable/index.md
View file

@ -1,5 +1,5 @@
---
title: "[Pre-Release] v1.74.0"
title: "v1.74.0-stable"
slug: "v1-74-0-stable"
date: 2025-07-05T10:00:00
authors:
@ -28,14 +28,14 @@ import TabItem from '@theme/TabItem';
docker run \
-e STORE_MODEL_IN_DB=True \
-p 4000:4000 \
ghcr.io/berriai/litellm:v1.74.0.rc
ghcr.io/berriai/litellm:v1.74.0-stable
```
</TabItem>
<TabItem value="pip" label="Pip">
``` showLineNumbers title="pip install litellm"
pip install litellm==1.74.0.post1
pip install litellm==1.74.0.post2
```
</TabItem>
@ -45,24 +45,19 @@ pip install litellm==1.74.0.post1
## Key Highlights
### Azure Content Safety Guardrails
<Image
img={require('../../img/azure_content_safety_guardrails.jpg')}
style={{width: '100%', display: 'block', margin: '2rem auto'}}
/>
<br />
- **MCP Gateway Namespace Servers** - Clients connecting to LiteLLM can now specify which MCP servers to use.
- **Key/Team Based Logging on UI** - Proxy Admins can configure team or key-based logging settings directly in the UI.
- **Azure Content Safety Guardrails** - Added support for prompt injection and text moderation with Azure Content Safety Guardrails.
- **VertexAI Deepseek Models** - Support for calling VertexAI Deepseek models with LiteLLM's/chat/completions or /responses API.
- **Github Copilot API** - You can now use Github Copilot as an LLM API provider.
LiteLLM now supports **Azure Content Safety Guardrails** for Prompt Injection and Text Moderation. This is **great for internal chat-ui** use cases, as you can now create guardrails with detection for Azure’s Harm Categories, specify custom severity thresholds and run them across 100+ LLMs for just that use-case (or across all your calls).
### MCP Gateway: Namespaced MCP Servers
[Get Started](../../docs/proxy/guardrails/azure_content_guardrail)
This release brings support for namespacing MCP Servers on LiteLLM MCP Gateway. This means you can specify the `x-mcp-servers` header to specify which servers to list tools from.
This is useful when you want to point MCP clients to specific MCP Servers on LiteLLM.
### MCP Gateway: Segregate MCP tools
MCP Server Segregation is now supported on LiteLLM. This means you can specify the `x-mcp-servers` header to specify which servers to list tools from. This is useful when you want to request tools from only a subset of configured servers — enabling curated toolsets and cleaner control.
#### Usage
@ -163,7 +158,19 @@ For developers using LiteLLM, their logs are automatically routed to their speci
- `arize`
- `langsmith`
### Azure Content Safety Guardrails
<Image
img={require('../../img/azure_content_safety_guardrails.jpg')}
style={{width: '100%', display: 'block', margin: '2rem auto'}}
/>
<br />
LiteLLM now supports **Azure Content Safety Guardrails** for Prompt Injection and Text Moderation. This is **great for internal chat-ui** use cases, as you can now create guardrails with detection for Azure’s Harm Categories, specify custom severity thresholds and run them across 100+ LLMs for just that use-case (or across all your calls).
[Get Started](../../docs/proxy/guardrails/azure_content_guardrail)
### Python SDK: 2.3 Second Faster Import Times

28
litellm/model_prices_and_context_window_backup.json
View file

@ -4544,6 +4544,34 @@
"supports_tool_choice": true,
"supports_response_schema": true
},
"mistral/devstral-small-2507": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 3e-07,
"litellm_provider": "mistral",
"mode": "chat",
"source": "https://mistral.ai/news/devstral",
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_tool_choice": true,
"supports_response_schema": true
},
"mistral/devstral-medium-2507": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 4e-07,
"output_cost_per_token": 2e-06,
"litellm_provider": "mistral",
"mode": "chat",
"source": "https://mistral.ai/news/devstral",
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_tool_choice": true,
"supports_response_schema": true
},
"mistral/magistral-medium-latest": {
"max_tokens": 40000,
"max_input_tokens": 40000,