Google (Gemma) models

Google's open Gemma models, including multimodal versions. The honest, $0-markup cost to run each — free on your machine, a rented GPU, or your own API key.

Gemma 2 9B Instruct — 9B, Google · $0.06/1M API
Gemma 3 27B — 27B, Google · $0.32/1M API
gemma 3 270m — 300M, google · $0.10/1M API
Gemma 3 12B — 12B, Google · $0.20/1M API
Gemma 2 27B Instruct — 27B, Google · $0.65/1M API
gemma 3 1b it — 1B, google · $0.11/1M API
gemma 2 2b it — 2.6B, google · $0.12/1M API
gemma 2b — 2.5B, google · $0.12/1M API
gemma 2 2b — 2.6B, google · $0.12/1M API
gemma 1.1 2b it — 2.5B, google · $0.12/1M API
gemma 3 270m it — 300M, google · $0.10/1M API
functiongemma 270m it — 300M, google · $0.10/1M API
gemma 2 9b — 9.2B, google · $0.17/1M API
gemma 2b it — 2.5B, google · $0.12/1M API
gemma 7b — 8.5B, google · $0.17/1M API

Other publishers

Qwen (Alibaba) · Meta Llama · DeepSeek · Microsoft (Phi) · Mistral AI · NVIDIA · OpenAI (gpt-oss) · IBM Granite · Z.ai (GLM) · Moonshot AI (Kimi) · MiniMax · Cohere · Ai2 (OLMo) · Nous Research · Liquid AI · TII (Falcon) · EleutherAI · InternLM · Xiaomi (MiMo)

All models → · Compare →