Compare models
Pick up to 4. Every model here is free in free-pi.
| Defense Flash | Gemini 4 Argon | DeepSeek V4 Pro | GPT-6 Luna | |
|---|---|---|---|---|
| Maker | — | DeepSeek | OpenAI | |
| Usage in free-pi | ~20x usage | premium, uses allowance fast · ~41x usage | ~8.6x usage | ~2.0x usage |
| Intelligence index | — | 52.6 (best) | 30.4 | 38.1 |
| Coding index | — | — | 59.4 | — |
| Context window | — | 1,048,576 tokens | 1,048,576 tokens | 1,050,000 tokens (best) |
| Max output | — | 943,718 tokens (best) | 384,000 tokens | 128,000 tokens |
| Inputs | — | Text, image, file, audio, video (best) | Text | Text, image, file |
| Tool calling | — | Yes | Yes | Yes |
| Reasoning effort | — | Yes | Yes | Yes |
| Structured output | — | Yes | Yes | Yes |
| Released | — | Oct 13, 2026 | Apr 24, 2026 | Sep 22, 2026 |
| Model page | Model page | Model page | Model page | Model page |
Stats from OpenRouter; refreshed automatically. Usage rate from free-pi. Green marks the best value in each row. “—” means no figure is available.