Compare models
Pick up to 4. Every model here is free in free-pi.
GPT-OSS 120B Kimi K3.1 Pro Gemini 4 Argon
+ Add model
- DeepSeek V4 Flash
- Claude Haiku 5.5
- Claude Sonnet 5.5
- DeepSeek V4.1 Flash
- DeepSeek V4 Pro
- Defense Flash
- Defense Flash 2
- Gemini 4 Argon Flex
- GLM 5.3 Flash
- GPT-6.1 Sol
- GPT-6.1 Sol Flex
- GPT-6 Luna
- GPT-6 Luna Flex
- Laguna S 2.1 (Poolside)
- MiMo V2.6 Flash (Xiaomi)
- Muse Spark 1.3 Contributor
- Muse Spark Open (Meta)
- Qwen3.5 35B (Darkbloom)
- Solar Pro 4
| GPT-OSS 120B | Kimi K3.1 Pro | Gemini 4 Argon | |
|---|---|---|---|
| Maker | OpenAI | MoonshotAI | |
| Usage in free-pi | ~0.6x usage | ~41x usage | premium, uses allowance fast · ~41x usage |
| Intelligence index | 11.6 | — | 52.6 (best) |
| Coding index | 30.4 | — | — |
| Context window | 131,072 tokens | 1,048,576 tokens (best) | 1,048,576 tokens (best) |
| Max output | 65,536 tokens | 943,718 tokens (best) | 943,718 tokens (best) |
| Inputs | Text | Text, image, video | Text, image, file, audio, video (best) |
| Tool calling | Yes | Yes | Yes |
| Reasoning effort | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Released | Aug 5, 2025 | Oct 23, 2026 | Oct 13, 2026 |
| 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.