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 new file mode 100644 index 0000000000..9ef4bacb2a --- /dev/null +++ b/docs/my-website/blog/gemini_3_1_flash_lite/index.md @@ -0,0 +1,175 @@ +--- +slug: gemini_3_1_flash_lite_preview +title: "DAY 0 Support: Gemini 3.1 Flash Lite Preview on LiteLLM" +date: 2026-03-03T08:00:00 +authors: + - name: Sameer Kankute + title: SWE @ LiteLLM (LLM Translation) + url: https://www.linkedin.com/in/sameer-kankute/ + image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg + - 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 +description: "Guide to using Gemini 3.1 Flash Lite Preview on LiteLLM Proxy and SDK with day 0 support." +tags: [gemini, day 0 support, llms, supernova] +hide_table_of_contents: false +--- + + +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +# Gemini 3.1 Flash Lite Preview Day 0 Support + +LiteLLM now supports `gemini-3.1-flash-lite-preview` with full day 0 support! + +:::note +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. +::: + +## Deploy this version + + + + +``` showLineNumbers title="docker run litellm" +docker run \ +-e STORE_MODEL_IN_DB=True \ +-p 4000:4000 \ +ghcr.io/berriai/litellm:main-v1.80.8-stable.1 +``` + + + + + +``` showLineNumbers title="pip install litellm" +pip install litellm==v1.80.8-stable.1 +``` + + + + +## What's New + +Supports all four thinking levels: +- **MINIMAL**: Ultra-fast responses with minimal reasoning +- **LOW**: Simple instruction following +- **MEDIUM**: Balanced reasoning for complex tasks +- **HIGH**: Maximum reasoning depth (dynamic) + +--- + +## Quick Start + + + + +**Basic Usage** + +```python +from litellm import completion + +response = completion( + model="gemini/gemini-3.1-flash-lite-preview", + messages=[{"role": "user", "content": "Extract key entities from this text: ..."}], +) + +print(response.choices[0].message.content) +``` + +**With Thinking Levels** + +```python +from litellm import completion + +# Use MEDIUM thinking for complex reasoning tasks +response = completion( + model="gemini/gemini-3.1-flash-lite-preview", + messages=[{"role": "user", "content": "Analyze this dataset and identify patterns"}], + reasoning_effort="medium", # low, medium , high +) + +print(response.choices[0].message.content) +``` + + + + + +**1. Setup config.yaml** + +```yaml +model_list: + - model_name: gemini-3.1-flash-lite + litellm_params: + model: gemini/gemini-3.1-flash-lite-preview + api_key: os.environ/GEMINI_API_KEY + + # Or use Vertex AI + - model_name: vertex-gemini-3.1-flash-lite + litellm_params: + model: vertex_ai/gemini-3.1-flash-lite-preview + vertex_project: your-project-id + vertex_location: us-central1 +``` + +**2. Start proxy** + +```bash +litellm --config /path/to/config.yaml +``` + +**3. Make requests** + +```bash +curl -X POST http://localhost:4000/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer " \ + -d '{ + "model": "gemini-3.1-flash-lite", + "messages": [{"role": "user", "content": "Extract structured data from this text"}], + "reasoning_effort": "low" + }' +``` + + + + +--- + +## Supported Endpoints + +LiteLLM provides **full end-to-end support** for Gemini 3.1 Flash Lite Preview 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](../../docs/generateContent.md) compatible endpoint + +All endpoints support: +- Streaming and non-streaming responses +- Function calling with thought signatures +- Multi-turn conversations +- All Gemini 3-specific features (thinking levels, thought signatures) +- Full multimodal support (text, image, audio, video) + +--- + +## `reasoning_effort` Mapping for Gemini 3.1 + +LiteLLM automatically maps OpenAI's `reasoning_effort` parameter to Gemini's `thinkingLevel`: + +| reasoning_effort | thinking_level | Use Case | +|------------------|----------------|----------| +| `minimal` | `minimal` | Ultra-fast responses, simple queries | +| `low` | `low` | Basic instruction following | +| `medium` | `medium` | Balanced reasoning for moderate complexity | +| `high` | `high` | Maximum reasoning depth, complex problems | +| `disable` | `minimal` | Disable extended reasoning | +| `none` | `minimal` | No extended reasoning | \ No newline at end of file diff --git a/docs/my-website/docs/providers/gemini.md b/docs/my-website/docs/providers/gemini.md index 6de2263916..f97f025c19 100644 --- a/docs/my-website/docs/providers/gemini.md +++ b/docs/my-website/docs/providers/gemini.md @@ -2041,6 +2041,7 @@ response = litellm.completion( | gemini-2.0-flash-lite-preview-02-05 | `completion(model='gemini/gemini-2.0-flash-lite-preview-02-05', messages)` | `os.environ['GEMINI_API_KEY']` | | gemini-2.5-flash-preview-09-2025 | `completion(model='gemini/gemini-2.5-flash-preview-09-2025', messages)` | `os.environ['GEMINI_API_KEY']` | | gemini-2.5-flash-lite-preview-09-2025 | `completion(model='gemini/gemini-2.5-flash-lite-preview-09-2025', messages)` | `os.environ['GEMINI_API_KEY']` | +| gemini-3.1-flash-lite-preview | `completion(model='gemini/gemini-3.1-flash-lite-preview', messages)` | `os.environ['GEMINI_API_KEY']` | | gemini-flash-latest | `completion(model='gemini/gemini-flash-latest', messages)` | `os.environ['GEMINI_API_KEY']` | | gemini-flash-lite-latest | `completion(model='gemini/gemini-flash-lite-latest', messages)` | `os.environ['GEMINI_API_KEY']` | diff --git a/docs/my-website/docs/providers/vertex.md b/docs/my-website/docs/providers/vertex.md index 63e4dceec0..94619082e8 100644 --- a/docs/my-website/docs/providers/vertex.md +++ b/docs/my-website/docs/providers/vertex.md @@ -1685,6 +1685,7 @@ litellm.vertex_location = "us-central1 # Your Location | gemini-2.5-pro | `completion('gemini-2.5-pro', messages)`, `completion('vertex_ai/gemini-2.5-pro', messages)` | | gemini-2.5-flash-preview-09-2025 | `completion('gemini-2.5-flash-preview-09-2025', messages)`, `completion('vertex_ai/gemini-2.5-flash-preview-09-2025', messages)` | | gemini-2.5-flash-lite-preview-09-2025 | `completion('gemini-2.5-flash-lite-preview-09-2025', messages)`, `completion('vertex_ai/gemini-2.5-flash-lite-preview-09-2025', messages)` | +| gemini-3.1-flash-lite-preview | `completion('gemini-3.1-flash-lite-preview', messages)`, `completion('vertex_ai/gemini-3.1-flash-lite-preview', messages)` | ## Private Service Connect (PSC) Endpoints diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4934f11d45..5de764c5ce 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -14334,6 +14334,57 @@ "supports_vision": true, "supports_web_search": true }, + "gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -17090,6 +17141,59 @@ "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "supports_service_tier": true }, + "gemini/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000 + }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_audio_token": 1e-06, @@ -32302,6 +32406,57 @@ "output_cost_per_token": 3e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, + "vertex_ai/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9c11c8a9d4..412f99791a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -14450,6 +14450,57 @@ "supports_vision": true, "supports_web_search": true }, + "gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -17206,6 +17257,59 @@ "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, "supports_service_tier": true }, + "gemini/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000 + }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, "input_cost_per_audio_token": 1e-06, @@ -32524,6 +32628,57 @@ "output_cost_per_token": 3e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" }, + "vertex_ai/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 7e8848be30..2e033b6f06 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -33,8 +33,8 @@ sys.path.insert( ) # Adds the parent directory to the system path from litellm.litellm_core_utils.llm_cost_calc.utils import ( - _calculate_input_cost, PromptTokensDetailsResult, + _calculate_input_cost, calculate_cache_writing_cost, generic_cost_per_token, ) @@ -127,6 +127,52 @@ def test_reasoning_tokens_gemini(): ) +def test_reasoning_tokens_gemini_3_1_flash_lite(): + """Test cost calculation for gemini-3.1-flash-lite-preview with reasoning tokens""" + model = "gemini-3.1-flash-lite-preview" + custom_llm_provider = "gemini" + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + usage = Usage( + completion_tokens=1000, + prompt_tokens=500, + total_tokens=1500, + completion_tokens_details=CompletionTokensDetailsWrapper( + accepted_prediction_tokens=None, + audio_tokens=None, + reasoning_tokens=400, + rejected_prediction_tokens=None, + text_tokens=600, + ), + prompt_tokens_details=PromptTokensDetailsWrapper( + audio_tokens=None, cached_tokens=None, text_tokens=500, image_tokens=None + ), + ) + model_cost_map = litellm.model_cost[model] + prompt_cost, completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider=custom_llm_provider, + ) + + assert round(prompt_cost, 10) == round( + model_cost_map["input_cost_per_token"] * usage.prompt_tokens, + 10, + ) + assert round(completion_cost, 10) == round( + ( + model_cost_map["output_cost_per_token"] + * usage.completion_tokens_details.text_tokens + ) + + ( + model_cost_map["output_cost_per_reasoning_token"] + * usage.completion_tokens_details.reasoning_tokens + ), + 10, + ) + + def test_image_tokens_with_custom_pricing(): """Test that image_tokens in completion are properly costed with output_cost_per_image_token.""" from unittest.mock import patch