Gemini 3 Pro vs Llama-4-Maverick-17B-128E-Instruct-FP8
Llama-4-Maverick-17B-128E-Instruct-FP8 is cheaper on output tokens, while Gemini 3 Pro offers a larger context window. Choose Gemini 3 Pro or Llama-4-Maverick-17B-128E-Instruct-FP8 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Gemini 3 Pro | Llama-4-Maverick-17B-128E-Instruct-FP8 |
|---|---|---|
| Provider | OpenCode | Vercel AI Gateway |
| Input / 1M tokens | $2.00 | $0.24 |
| Output / 1M tokens | $12.00 | $0.97 |
| Context window | 1M | 128K |
| Parameters | — | — |
| Open weights | No | Yes |
| Released | Nov 2025 | Apr 2025 |
| LiveBench score | 73.5 | — |
| LMArena (Chatbot Arena) Elo score | 1479 | — |
| LMArena WebDev Elo score | 1440 | — |
| LMArena Vision Elo score | 1305 | — |
| SWE-bench Multilingual score | 68.7 | — |
| Epoch Capabilities Index score | 153 | — |
| GPQA Diamond score | — | 67.0 |
| FrontierMath score | — | 0.7 |
FAQ
Is Gemini 3 Pro or Llama-4-Maverick-17B-128E-Instruct-FP8 cheaper?
Llama-4-Maverick-17B-128E-Instruct-FP8 is cheaper on output tokens ($0.97 vs $12.00 per 1M).
Which has the larger context window, Gemini 3 Pro or Llama-4-Maverick-17B-128E-Instruct-FP8?
Gemini 3 Pro has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.