Compare models
Pick up to 4. Every model here is free in free-pi.
| DeepSeek V4 Flash | GPT-6.1 Sol | Defense Flash | DeepSeek V4 Pro | |
|---|---|---|---|---|
| Maker | DeepSeek | OpenAI | — | DeepSeek |
| Usage in free-pi | 1x usage (default) | premium, uses allowance fast · ~41x usage | ~20x usage | ~8.6x usage |
| Intelligence index | 34.3 | 51.8 (best) | — | 30.4 |
| Coding index | 69.1 (best) | — | — | 59.4 |
| Context window | 1,048,576 tokens | 1,050,000 tokens (best) | — | 1,048,576 tokens |
| Max output | 131,072 tokens | 128,000 tokens | — | 384,000 tokens (best) |
| Inputs | Text | Text, image, file (best) | — | Text |
| Tool calling | Yes | Yes | — | Yes |
| Reasoning effort | Yes | Yes | — | Yes |
| Structured output | Yes | Yes | — | Yes |
| Released | Jul 31, 2026 | Sep 29, 2026 | — | Apr 24, 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.