From 81262743d3a5c69034d307deb53c4ae56a09af3f Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Tue, 16 Dec 2025 20:14:11 +0530 Subject: [PATCH] Add gemini 3 flash blog --- docs/my-website/blog/gemini_3_flash/index.md | 219 +++++++++++++++++++ 1 file changed, 219 insertions(+) create mode 100644 docs/my-website/blog/gemini_3_flash/index.md diff --git a/docs/my-website/blog/gemini_3_flash/index.md b/docs/my-website/blog/gemini_3_flash/index.md new file mode 100644 index 00000000000..5954b3fd05e --- /dev/null +++ b/docs/my-website/blog/gemini_3_flash/index.md @@ -0,0 +1,219 @@ +--- +slug: gemini_3_flash +title: "DAY 0 Support: Gemini 3 Flash on LiteLLM" +date: 2025-11-19T10:00:00 +authors: + - name: Sameer Kankute + title: SWE @ LiteLLM (LLM Translation) + url: https://www.linkedin.com/in/sameer-kankute/ + image_url: https://media.licdn.com/dms/image/v2/D4D03AQHB_loQYd5gjg/profile-displayphoto-shrink_800_800/profile-displayphoto-shrink_800_800/0/1719137160975?e=1765411200&v=beta&t=c8396f--_lH6Fb_pVvx_jGholPfcl0bvwmNynbNdnII + - name: Krrish Dholakia + title: "CEO, LiteLLM" + url: https://www.linkedin.com/in/krish-d/ + image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg + - name: Ishaan Jaff + title: "CTO, LiteLLM" + url: https://www.linkedin.com/in/reffajnaahsi/ + image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg +tags: [gemini, day 0 support, llms] +hide_table_of_contents: false +--- + + +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +# Gemini 3 Flash Day 0 Support + +LiteLLM now supports `gemini-3-flash` and all the new API changes along with it. + +## What's New + +### 1. New Thinking Levels: `thinkingLevel` with MINIMAL & MEDIUM + +Gemini 3 Flash introduces granular thinking control with `thinkingLevel` instead of `thinkingBudget`. +- **MINIMAL**: Ultra-lightweight thinking for fast responses +- **MEDIUM**: Balanced thinking for complex reasoning +- **HIGH**: Maximum reasoning depth + +### 2. Thought Signatures + +Like `gemini-3-pro`, this model also includes thought signatures for tool calls. LiteLLM handles signature extraction and embedding internally. [Learn more about thought signatures](../gemini_3/index.md#thought-signatures). + +--- +## Supported Endpoints + +LiteLLM provides **full end-to-end support** for Gemini 3 Flash on: + +- ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint +- ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming) +- ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint +- ✅ `/v1/generateContent` – [Google Gemini API](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#rest) compatible endpoint (for code, see: `client.models.generate_content(...)`) + +All endpoints support: +- Streaming and non-streaming responses +- Function calling with thought signatures +- Multi-turn conversations +- All Gemini 3-specific features +- Converstion of provider specific thinking related param to thinkingLevel + +## Quick Start + + + + +**Basic Usage with MEDIUM thinking (NEW)** + +```python +from litellm import completion + +# No need to make any changes to your code as we map openai reasoning param to thinkingLevel +response = completion( + model="gemini-3-flash", + messages=[{"role": "user", "content": "Solve this complex math problem: 25 * 4 + 10"}], + reasoning_effort="medium", # NEW: MEDIUM thinking level +) + +print(response.choices[0].message.content) +``` + + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: gemini-3-flash + litellm_params: + model: gemini/gemini-3-flash + api_key: os.environ/GEMINI_API_KEY +``` + +**2. Start proxy** + +```bash +litellm --config /path/to/config.yaml +``` + +**3. Call with MEDIUM thinking** + +```bash +curl http://localhost:4000/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer " \ + -d '{ + "model": "gemini-3-flash-reasoning", + "messages": [{"role": "user", "content": "Complex reasoning task"}], + "reasoning_effort": "medium" + }' +``` + + + + +--- + +## All `reasoning_effort` Levels + + + + +**Ultra-fast, minimal reasoning** + +```python +from litellm import completion + +response = completion( + model="gemini-3-flash", + messages=[{"role": "user", "content": "What's 2+2?"}], + reasoning_effort="minimal", +) +``` + + + + + +**Simple instruction following** + +```python +response = completion( + model="gemini-3-flash", + messages=[{"role": "user", "content": "Write a haiku about coding"}], + reasoning_effort="low", +) +``` + + + + + +**Balanced reasoning for complex tasks** ✨ + +```python +response = completion( + model="gemini-3-flash", + messages=[{"role": "user", "content": "Analyze this dataset and find patterns"}], + reasoning_effort="medium", # NEW! +) +``` + + + + + +**Maximum reasoning depth** + +```python +response = completion( + model="gemini-3-flash", + messages=[{"role": "user", "content": "Prove this mathematical theorem"}], + reasoning_effort="high", +) +``` + + + + +--- + +## Key Features + +✅ **Thinking Levels**: MINIMAL, LOW, MEDIUM, HIGH +✅ **Thought Signatures**: Track reasoning with unique identifiers +✅ **Seamless Integration**: Works with existing OpenAI-compatible client +✅ **Backward Compatible**: Gemini 2.5 models continue using `thinkingBudget` + +--- + +## Installation + +```bash +pip install litellm --upgrade +``` + +```python +import litellm +from litellm import completion + +response = completion( + model="gemini-3-flash", + messages=[{"role": "user", "content": "Your question here"}], + reasoning_effort="medium", # Use MEDIUM thinking +) +print(response) +``` + +## `reasoning_effort` Mapping for Gemini 3+ + +| reasoning_effort | thinking_level | +|------------------|----------------| +| `minimal` | `minimal` | +| `low` | `low` | +| `medium` | `medium` | +| `high` | `high` | +| `disable` | `minimal` | +| `none` | `minimal` | +