Google: Gemma 3n 4B

Gemma 3n 4B is a text-only model from Google with a 32,768-token context window. It does not support tool use, reasoning modes, or structured output, and it accepts no image or audio input. Those constraints make it a straightforward text-completion model without the agentic or multimodal features found in larger offerings. At $0.06 per million input tokens and $0.12 per million output tokens, it sits at the budget end of the market, which is its clearest argument for consideration. Its blended benchmark score of 5.9 comes from a single benchmark, so competitive comparisons should be treated with caution until broader coverage is available. Developers running high-volume, text-only workloads who can tolerate limited benchmark evidence and do not need tools or structured output will find the pricing worth evaluating, but teams requiring richer capabilities should look elsewhere.