From 57f2af8ea73cac2ff32c259ac989bc4829c0ae43 Mon Sep 17 00:00:00 2001 From: Arindam200 Date: Tue, 17 Mar 2026 02:14:23 +0530 Subject: [PATCH] Included truncation comments for improved readability in markdown files. --- .../blog/anthropic_opus_4_5_and_advanced_features/index.md | 2 ++ docs/my-website/blog/claude_opus_4_6/index.md | 2 ++ docs/my-website/blog/claude_sonnet_4_6/index.md | 2 ++ docs/my-website/blog/gemin_3.1/index.md | 2 ++ docs/my-website/blog/gemini_3/index.md | 2 ++ docs/my-website/blog/gemini_3_1_flash_lite/index.md | 2 ++ docs/my-website/blog/gemini_3_flash/index.md | 2 ++ docs/my-website/blog/gemini_embedding_2_multimodal/index.md | 2 ++ docs/my-website/blog/gpt_5_3_codex/index.md | 2 ++ docs/my-website/blog/gpt_5_4/index.md | 2 ++ docs/my-website/blog/httpx_cache_eviction_incident/index.md | 2 ++ docs/my-website/blog/litellm_observatory/index.md | 3 ++- docs/my-website/blog/minimax_m2_5/index.md | 2 ++ docs/my-website/blog/realtime_webrtc_http_endpoints/index.md | 3 ++- docs/my-website/blog/sub_millisecond_proxy_overhead/index.md | 2 ++ docs/my-website/blog/video_characters_litellm/index.md | 4 +++- 16 files changed, 33 insertions(+), 3 deletions(-) diff --git a/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md b/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md index 0b0176f4c0..21ba3d6079 100644 --- a/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md +++ b/docs/my-website/blog/anthropic_opus_4_5_and_advanced_features/index.md @@ -16,6 +16,8 @@ import TabItem from '@theme/TabItem'; This guide covers Anthropic's latest model (Claude Opus 4.5) and its advanced features now available in LiteLLM: Tool Search, Programmatic Tool Calling, Tool Input Examples, and the Effort Parameter. +{/* truncate */} + --- | Feature | Supported Models | diff --git a/docs/my-website/blog/claude_opus_4_6/index.md b/docs/my-website/blog/claude_opus_4_6/index.md index ab1789f9b7..eeb5d5ff2f 100644 --- a/docs/my-website/blog/claude_opus_4_6/index.md +++ b/docs/my-website/blog/claude_opus_4_6/index.md @@ -16,6 +16,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports Claude Opus 4.6 on Day 0. Use it across Anthropic, Azure, Vertex AI, and Bedrock through the LiteLLM AI Gateway. +{/* truncate */} + ## Docker Image ```bash diff --git a/docs/my-website/blog/claude_sonnet_4_6/index.md b/docs/my-website/blog/claude_sonnet_4_6/index.md index 3ae5a6db30..12446c82c6 100644 --- a/docs/my-website/blog/claude_sonnet_4_6/index.md +++ b/docs/my-website/blog/claude_sonnet_4_6/index.md @@ -15,6 +15,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports Claude Sonnet 4.6 on Day 0. Use it across Anthropic, Azure, Vertex AI, and Bedrock through the LiteLLM AI Gateway. +{/* truncate */} + ## Docker Image ```bash diff --git a/docs/my-website/blog/gemin_3.1/index.md b/docs/my-website/blog/gemin_3.1/index.md index a125c3bf29..0afccb49d9 100644 --- a/docs/my-website/blog/gemin_3.1/index.md +++ b/docs/my-website/blog/gemin_3.1/index.md @@ -19,6 +19,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports `gemini-3.1-pro-preview` and all the new API changes along with it. +{/* truncate */} + ## Deploy this version diff --git a/docs/my-website/blog/gemini_3/index.md b/docs/my-website/blog/gemini_3/index.md index 4c39ea5aab..a5b94382b6 100644 --- a/docs/my-website/blog/gemini_3/index.md +++ b/docs/my-website/blog/gemini_3/index.md @@ -20,6 +20,8 @@ This guide covers common questions and best practices for using `gemini-3-pro-pr ::: +{/* truncate */} + ## Quick Start diff --git a/docs/my-website/blog/gemini_3_1_flash_lite/index.md b/docs/my-website/blog/gemini_3_1_flash_lite/index.md index 3d4861f6d1..0ae79e5fa6 100644 --- a/docs/my-website/blog/gemini_3_1_flash_lite/index.md +++ b/docs/my-website/blog/gemini_3_1_flash_lite/index.md @@ -23,6 +23,8 @@ LiteLLM now supports `gemini-3.1-flash-lite-preview` with full day 0 support! If you only want cost tracking, you need no change in your current Litellm version. But if you want the support for new features introduced along with it like thinking levels, you will need to use v1.80.8-stable.1 or above. ::: +{/* truncate */} + ## Deploy this version diff --git a/docs/my-website/blog/gemini_3_flash/index.md b/docs/my-website/blog/gemini_3_flash/index.md index e708603d11..5e98d2136b 100644 --- a/docs/my-website/blog/gemini_3_flash/index.md +++ b/docs/my-website/blog/gemini_3_flash/index.md @@ -23,6 +23,8 @@ LiteLLM now supports `gemini-3-flash-preview` and all the new API changes along If you only want cost tracking, you need no change in your current Litellm version. But if you want the support for new features introduced along with it like thinking levels, you will need to use v1.80.8-stable.1 or above. ::: +{/* truncate */} + ## Deploy this version diff --git a/docs/my-website/blog/gemini_embedding_2_multimodal/index.md b/docs/my-website/blog/gemini_embedding_2_multimodal/index.md index 1fbc9bc53f..d66de1b6c7 100644 --- a/docs/my-website/blog/gemini_embedding_2_multimodal/index.md +++ b/docs/my-website/blog/gemini_embedding_2_multimodal/index.md @@ -16,6 +16,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports **multimodal embeddings** with `gemini-embedding-2-preview`—generating a single embedding from a mix of text, images, audio, video, and PDF content. Available via both the **Gemini API** (API key) and **Vertex AI** (GCP credentials). +{/* truncate */} + ## Supported Input Types | Modality | Supported Formats | diff --git a/docs/my-website/blog/gpt_5_3_codex/index.md b/docs/my-website/blog/gpt_5_3_codex/index.md index b45bb60b09..1dfab1f7ac 100644 --- a/docs/my-website/blog/gpt_5_3_codex/index.md +++ b/docs/my-website/blog/gpt_5_3_codex/index.md @@ -16,6 +16,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports GPT-5.3-Codex on Day 0, including support for the new assistant `phase` metadata on Responses API output items. +{/* truncate */} + ## Why `phase` matters for GPT-5.3-Codex `phase` appears on assistant output items and helps distinguish preamble/commentary turns from final closeout responses. diff --git a/docs/my-website/blog/gpt_5_4/index.md b/docs/my-website/blog/gpt_5_4/index.md index be0ea0f6d4..4f7e434415 100644 --- a/docs/my-website/blog/gpt_5_4/index.md +++ b/docs/my-website/blog/gpt_5_4/index.md @@ -16,6 +16,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports fully GPT-5.4! +{/* truncate */} + ## Docker Image ```bash diff --git a/docs/my-website/blog/httpx_cache_eviction_incident/index.md b/docs/my-website/blog/httpx_cache_eviction_incident/index.md index 6e687d2dbf..7fc3789a91 100644 --- a/docs/my-website/blog/httpx_cache_eviction_incident/index.md +++ b/docs/my-website/blog/httpx_cache_eviction_incident/index.md @@ -23,6 +23,8 @@ A change to improve Redis connection pool cleanup introduced a regression that c **Impact:** Any proxy instance that hit the cache TTL (default 10 minutes) or capacity limit (200 entries) would have its httpx clients closed out from under it, causing requests to LLM providers to fail with connection errors. +{/* truncate */} + --- ## Background diff --git a/docs/my-website/blog/litellm_observatory/index.md b/docs/my-website/blog/litellm_observatory/index.md index 073d11e14b..36366e5de2 100644 --- a/docs/my-website/blog/litellm_observatory/index.md +++ b/docs/my-website/blog/litellm_observatory/index.md @@ -19,6 +19,8 @@ As LiteLLM adoption has grown, so have expectations around reliability, performa This post introduces **LiteLLM Observatory**, a long-running release-validation system we built to catch regressions before they reach users. +{/* truncate */} + --- ## Why We Built the Observatory @@ -124,4 +126,3 @@ Reliability is an ongoing investment. LiteLLM Observatory is one of several systems we’re building to continuously raise the bar on release quality and operational safety. As LiteLLM evolves, so will our validation tooling, informed by real-world usage and lessons learned. We’ll continue to share those improvements openly as we go. - diff --git a/docs/my-website/blog/minimax_m2_5/index.md b/docs/my-website/blog/minimax_m2_5/index.md index b396725af1..9bccbdf797 100644 --- a/docs/my-website/blog/minimax_m2_5/index.md +++ b/docs/my-website/blog/minimax_m2_5/index.md @@ -16,6 +16,8 @@ import TabItem from '@theme/TabItem'; LiteLLM now supports MiniMax-M2.5 on Day 0. Use it across OpenAI-compatible and Anthropic-compatible APIs through the LiteLLM AI Gateway. +{/* truncate */} + ## Supported Models LiteLLM supports the following MiniMax models: diff --git a/docs/my-website/blog/realtime_webrtc_http_endpoints/index.md b/docs/my-website/blog/realtime_webrtc_http_endpoints/index.md index b9564172ae..70fc5b2c48 100644 --- a/docs/my-website/blog/realtime_webrtc_http_endpoints/index.md +++ b/docs/my-website/blog/realtime_webrtc_http_endpoints/index.md @@ -15,6 +15,8 @@ import WebRTCTester from '@site/src/components/WebRTCTester'; Connect to the Realtime API via WebRTC from browser/mobile clients. LiteLLM handles auth and key management. +{/* truncate */} + ## How it works ![WebRTC flow: Browser, LiteLLM Proxy, and OpenAI/Azure](../../img/webrtc_flow.png) @@ -107,4 +109,3 @@ A: Set the correct `api_version` in `litellm_params` (or via the `AZURE_API_VERS **Q: What if I get no audio?** A: Make sure you grant microphone permission, ensure `pc.ontrack` assigns the audio element with `autoplay` enabled, check your network/firewall for WebRTC traffic, and inspect the browser console for ICE or SDP errors. - diff --git a/docs/my-website/blog/sub_millisecond_proxy_overhead/index.md b/docs/my-website/blog/sub_millisecond_proxy_overhead/index.md index a594b0c897..7f8ac086a2 100644 --- a/docs/my-website/blog/sub_millisecond_proxy_overhead/index.md +++ b/docs/my-website/blog/sub_millisecond_proxy_overhead/index.md @@ -23,6 +23,8 @@ Proxy overhead refers to the latency introduced by LiteLLM itself, independent o To measure it, we run the same workload directly against the provider and through LiteLLM at identical QPS (for example, 1,000 QPS) and compare the latency delta. To reduce noise, the load generator, LiteLLM, and a mock LLM endpoint all run on the same machine, ensuring the difference reflects proxy overhead rather than network latency. +{/* truncate */} + --- ## Where We're Coming From diff --git a/docs/my-website/blog/video_characters_litellm/index.md b/docs/my-website/blog/video_characters_litellm/index.md index c357a628fc..a0f87385d8 100644 --- a/docs/my-website/blog/video_characters_litellm/index.md +++ b/docs/my-website/blog/video_characters_litellm/index.md @@ -13,6 +13,8 @@ hide_table_of_contents: false LiteLLM now supoports videos character, edit and extension apis. +{/* truncate */} + ## What's New Four new endpoints for video character operations: @@ -116,4 +118,4 @@ Router knows exactly which deployment to use **Behind the scenes:** - Character ID format: `character_` - Metadata includes: provider, model_id, original_character_id -- Transparent to you - just use the ID, LiteLLM handles routing \ No newline at end of file +- Transparent to you - just use the ID, LiteLLM handles routing