From 1374b9dc025adb1e20a3c1e89a8c6b6a64ce7327 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Sat, 7 Feb 2026 13:07:20 +0530 Subject: [PATCH] Update opus 4.6 blog with adaptive thinking --- docs/my-website/blog/claude_opus_4_6/index.md | 29 +++++++++++++++++-- 1 file changed, 27 insertions(+), 2 deletions(-) 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 75b088c533d..0397f1288f7 100644 --- a/docs/my-website/blog/claude_opus_4_6/index.md +++ b/docs/my-website/blog/claude_opus_4_6/index.md @@ -348,9 +348,29 @@ Compaction blocks are also supported in streaming mode. You'll receive: - The accumulated `compaction_blocks` in `provider_specific_fields` +## Adaptive Thinking + +LiteLLM supports adaptive thinking through the `reasoning_effort` parameter: + +```bash +curl --location 'http://0.0.0.0:4000/chat/completions' \ +--header 'Content-Type: application/json' \ +--header 'Authorization: Bearer $LITELLM_KEY' \ +--data '{ + "model": "claude-opus-4-6", + "messages": [ + { + "role": "user", + "content": "Solve this complex problem: What is the optimal strategy for..." + } + ], + "reasoning_effort": "high" +}' +``` + ## Effort Levels -Four effort levels available: `low`, `medium`, `high` (default), and `max`. Pass directly via the `effort` parameter: +Four effort levels available: `low`, `medium`, `high` (default), and `max`. Pass directly via the `output_config` parameter: ```bash curl --location 'http://0.0.0.0:4000/chat/completions' \ @@ -364,10 +384,15 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \ "content": "Explain quantum computing" } ], - "effort": "max" + "output_config": { + "effort": "medium" + } + }' ``` +You can use reasoning effort plus output_config to have more control on the model. + ## 1M Token Context (Beta) Opus 4.6 supports 1M token context. Premium pricing applies for prompts exceeding 200k tokens ($10/$37.50 per million input/output tokens). LiteLLM supports cost calculations for 1M token contexts.