Google models
43 Google models you can call through UberLLM’s OpenAI-compatible API. The cheapest is Gemma 3 4B IT at $0.0005/1M input tokens, as of October 24, 2026. Every request is routed to the cheapest healthy seller; the price shown includes UberLLM’s 10% fee.
| Model | Price (from) | Context | Type | Capabilities |
|---|---|---|---|---|
| Gemma 4 Uncensored google/gemma-4-uncensored | $0.0894 in · $0.2749 out | 256K | Text | ToolsVisionJSON |
| Gemma 3 27B E2EE google/e2ee-gemma-3-27b | $0.0616 in · $0.2200 out | 40K | Text | ToolsJSON |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0027 in · $0.0163 out | 1049K | Text | ToolsVisionJSON |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3300 in · $2.64 out | 1049K | Text | ToolsVisionJSON |
| Gemma 3 27B google/gemma-3-27b-it | $0.0009 in · $0.0022 out | 40K | Text | ToolsJSON |
| Gemini 3.1 Pro google/gemini-3.1-pro | $0.2415 in · $1.45 out | 1049K | Text | ToolsVisionJSON |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0033 in · $0.0275 out | 1049K | Text | ToolsVisionJSON |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.0005 in · $0.0016 out | 262K | Text | ToolsVisionJSON |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.0013 in · $0.0040 out | 262K | Text | ToolsVisionJSON |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0055 in · $0.0330 out | 256K | Text | ToolsReasoningJSON |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6556 in · $3.93 out | 1000K | Text | ToolsReasoningJSON |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0165 in · $0.0990 out | 1049K | Text | ToolsJSON |
| Gemma 4 31B (E2EE) google/e2ee-gemma-4-31b | $0.1100 in · $0.3300 out | 262K | Text | ToolsJSON |
| Gemma 4 31B IT (Morpheus Web) google/gemma-4-31b-it:web | $0.1444 in · $0.4125 out | 262K | Text | ToolsVisionJSON |
| Gemma 4 26B A4B Uncensored (E2EE) google/e2ee-gemma-4-26b-a4b-uncensored-p | $0.0560 in · $0.2592 out | 262K | Text | ToolsJSON |
| Gemma 4 26B A4B IT (Morpheus Web) google/gemma-4-26b-a4b-it:web | $0.1341 in · $0.4125 out | 262K | Text | ToolsVisionJSON |
| Gemini 3.5 Flash Lite google/gemini-3-5-flash-lite | $0.1633 in · $1.36 out | 1000K | Text | ToolsReasoningVisionJSON |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.0005 in · $0.0016 out | 128K | Text | ToolsVisionJSON |
| Gemini 3.6 Flash google/gemini-3-6-flash | $0.4537 in · $2.27 out | 1000K | Text | ToolsReasoningVisionJSON |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.0005 in · $0.0007 out | 128K | Text | ToolsVisionJSON |
| Gemma 4 E2B google/gemma-4-e2b | $0.0022 in · $0.0044 out | 128K | Text | ToolsVisionJSON |
| Gemma 4 31B google/gemma-4-31b | $0.0010 in · $0.0030 out | 256K | Text | ToolsVisionJSON |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.1650 in · $0.8250 out | 1049K | Text | ToolsReasoningVisionJSON |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0063 in · $0.0317 out | 1049K | Text | ToolsReasoningVisionJSON |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.4352 in · $2.18 out | 1049K | Text | ToolsReasoningVisionJSON |
| Gemini 3.1 Flash TTS google/tts-gemini-3-1-flash | Audio | JSON | ||
| Veo 3 Fast Text-to-Video google/veo3-fast-text-to-video | $0.4 per video | Video | ||
| Veo 3.1 Fast Text-to-Video google/veo3-1-fast-text-to-video | $0.58 per video | Video | ||
| Nano Banana (Gemini 2.5 Flash Image) google/gemini-2.5-flash-image | Image | JSON | ||
| Veo 3 Full Text-to-Video google/veo3-full-text-to-video | $1.06 per video | Video | ||
| Veo 3.1 Full Text-to-Video google/veo3-1-full-text-to-video | $1.94 per video | Video | ||
| Veo3.1 Full (image-to-video) google/veo3-1-full-image-to-video | Video | |||
| Nano Banana 2 (image-to-image) google/nano-banana-2-edit | $0.11 per image | Image | JSON | |
| Gemini Omni Flash (reference-to-video) google/gemini-omni-flash-reference-to-video | $0.16 per video | Video | ||
| Veo3 Fast (image-to-video) google/veo3-fast-image-to-video | $0.0665 per video | Video | ||
| Veo3.1 Fast (image-to-video) google/veo3-1-fast-image-to-video | Video | |||
| Nano Banana Pro (image-to-image) google/nano-banana-pro-edit | $0.2 per image | Image | JSON | |
| Veo3 Full (image-to-video) google/veo3-full-image-to-video | $0.13 per video | Video | ||
| Nano Banana 2 Lite (image-to-image) google/nano-banana-2-lite-edit | $0.066 per image | Image | JSON | |
| Gemini Omni Flash (image-to-video) google/gemini-omni-flash-image-to-video | $0.16 per video | Video | ||
| Nano Banana 2.1 (Venice) google/venice-nano-banana-2-1 | $0.11 per image | Image | JSON | |
| Nano Banana 2 Lite (Venice) google/venice-nano-banana-2-lite | $0.066 per image | Image | JSON | |
| Nano Banana 2.1 (image-to-image) google/nano-banana-2-1-edit | $0.11 per image | Image | JSON |
Compare Google models
Google models — FAQ
What is the cheapest Google model?
Gemma 3 4B IT is the cheapest Google model on UberLLM right now, at $0.0005/1M input tokens. UberLLM routes each request to the cheapest healthy seller and bills the price shown, which includes UberLLM's 10% fee.
How many Google models can I use through UberLLM?
43 Google models are on the UberLLM marketplace today. One OpenAI-compatible API key and base URL (https://api.uberllm.dev/v1) calls every one of them — no per-provider contracts.
How do I call a Google model with the API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM key, and the model id (for example "google/gemma-4-uncensored"). Anthropic SDKs work against https://api.uberllm.dev/v1/messages.