Compare models
Pick up to 4. Every model here is free in free-pi.
GPT-OSS 20B GPT-6.2 Astra DeepSeek V4.1 Flash
+ Add model
- Particle-1
- GLM 5.3 Flash
- DeepSeek V4 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
- Hy4 Flash
- 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 | GPT-OSS 20B | GPT-6.2 Astra | DeepSeek V4.1 Flash |
|---|---|---|---|
| Maker | OpenAI | OpenAI | DeepSeek |
| Usage in free-pi | ~0.3x usage | ~51x usage | 🔥 Free Unlimited: limited time |
| Intelligence index | — | 62.1 (best) | 32.6 |
| Coding index | — | — | — |
| Context window | 131,072 tokens | 1,050,000 tokens (best) | 1,048,576 tokens |
| Max output | 117,964 tokens | 128,000 tokens | 393,216 tokens (best) |
| Inputs | Text | Text, image, file (best) | Text, image |
| Tool calling | Yes | Yes | Yes |
| Reasoning effort | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Released | Aug 5, 2025 | Nov 17, 2026 | Oct 17, 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.