Compare models
Pick up to 4. Every model here is free in free-pi.
Hy4 Flash GPT-OSS 20B DeepSeek V4 Flash
+ Add model
- Particle-1
- DeepSeek V4.1 Flash
- GLM 5.3 Flash
- Abliterated Large Flash
- Abliterated Large V2
- DeepSeek V4.1 Flash 600tps
- DeepSeek V4.1 Flash Abliterated
- DeepSeek V4 Pro
- Gemma 4 Uncensored
- GLM 4.7 Flash Heretic
- GPT-6.2 Astra
- Kimi K3.1 Pro
- Ling 3.0 Flash
- Ling 3.1 Flash
- MiMo V2.6 Flash (Xiaomi)
- Qwen3.5 35B
- Qwen 3.6 Plus Uncensored
- Qwen 3.7 Flash
- Solar Mini 4
- Solar Pro 4
- Uncensored 1.2
| Attribute | Hy4 Flash | GPT-OSS 20B | DeepSeek V4 Flash |
|---|---|---|---|
| Maker | Tencent | OpenAI | DeepSeek |
| Usage in free-pi | ~0.2x usage | ~0.3x usage | 🔥 Free Unlimited: limited time (default) |
| Intelligence index | — | — | — |
| Coding index | — | — | — |
| Context window | 1,048,576 tokens (best) | 131,072 tokens | 1,048,576 tokens (best) |
| Max output | 65,536 tokens | 117,964 tokens | 384,000 tokens (best) |
| Inputs | Text, image (best) | Text | Text |
| Tool calling | Yes | Yes | Yes |
| Reasoning effort | No | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Released | Nov 16, 2026 | Aug 5, 2025 | Jul 31, 2026 |
| Model page | Model page | Model page | Model page |
Stats refreshed automatically. Usage rate from free-pi. Green marks the best value in each row. “—” means no figure is available.