From 48af865358e19202350dbc3afc8802497cc85698 Mon Sep 17 00:00:00 2001 From: Mark McDonald Date: Thu, 26 Mar 2026 14:05:11 +0800 Subject: [PATCH] docs: add service_tier to gemini docs --- docs/my-website/docs/providers/gemini.md | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/docs/my-website/docs/providers/gemini.md b/docs/my-website/docs/providers/gemini.md index 87ab5ad40f4..1f3ede21e71 100644 --- a/docs/my-website/docs/providers/gemini.md +++ b/docs/my-website/docs/providers/gemini.md @@ -65,14 +65,13 @@ response = completion( - modalities - reasoning_content - audio (for TTS models only) +- service_tier **Anthropic Params** - thinking (used to set max budget tokens across anthropic/gemini models) [**See Updated List**](https://github.com/BerriAI/litellm/blob/main/litellm/llms/gemini/chat/transformation.py#L70) - - ## Usage - Thinking / `reasoning_content` LiteLLM translates OpenAI's `reasoning_effort` to Gemini's `thinking` parameter. [Code](https://github.com/BerriAI/litellm/blob/620664921902d7a9bfb29897a7b27c1a7ef4ddfb/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py#L362) @@ -298,6 +297,16 @@ curl http://0.0.0.0:4000/v1/chat/completions \ +## Usage - `service_tier` + +LiteLLM propagates OpenAI's `service_tier` parameter to Gemini, and also extracts it from the response headers (`x-gemini-service-tier`) into `model_response.service_tier`. + +| OpenAI `service_tier` | Gemini `service_tier` | Notes | +| --------------------- | --------------------- | ----- | +| `"auto"` | `"priority"` | LiteLLM maps OpenAI's `"auto"` to Gemini's `"priority"` tier, as `priority` will fall back on Gemini. | +| `"flex"` | `"flex"` | Direct mapping. | +| `"priority"` | `"priority"` | Direct mapping. | +| Any other value | Passed as-is | Unrecognized values are sent blindly so that the provider can reject the request directly if invalid. | ## Text-to-Speech (TTS) Audio Output