BETA
Mid-size Gemma 3 — fits on a single consumer GPU while keeping vision support.
Gemma 3 9B is a efficient AI model from Google. It costs $0.090 per million input tokens and $0.090 per million output tokens (blended $0.090/M), with a 128K-token context window.
Gemma 3 9B costs $0.090 per million input tokens and $0.090 per million output tokens, for a blended reference rate of $0.090 per million tokens.
Gemma 3 9B supports up to 128K tokens of context (128,000 tokens).
Gemma 3 9B is well suited to Single-GPU deployable, Vision and Open weights.
Gemma 3 9B is developed and served by Google.