Compare
Compare up to four models side by side on price, context window and capabilities. The best value in each row is highlighted, and the sliders below set the token counts used for the cost estimate.
Up to 4 models · the page URL is shareable
| Attribute | DeepSeek V4.1 Flash Hereticdeepseek-v4.1-flash-heretic | Apex Flash 1 Abliteratedglm-5.3-flash-abliterated | DeepSeek V4.1 Flash Uncensoreddeepseek-v4.1-flash-uncensored |
|---|---|---|---|
| Provider | DeepSeek | Z.ai | DeepSeek |
| Input priceper million tokens | $0.257 | $0.195Lowest | $0.429 |
| Output priceper million tokens | $1.03 | $0.650Lowest | $1.72 |
| Cached input priceper million tokens | $0.0172 | $0.0975 | $0.0107Lowest |
| Context window | 512K | 1MHighest | 1MHighest |
| Max output | 128K | 33K | 66K |
| Input modalities | Text, Image | Text, Image | Text, Image |
| Uncensored | |||
| Roleplay | — | — | — |
| Reasoning | |||
| Vision | |||
| Tool calling | |||
| Long context | |||
| Open weights | |||
| Coding | — | ||
| Released | 2026-10-31 | 2026-10-05 | 2026-10-01 |
| Cost of 1,000 requests3,000 input + 800 output tokens each | $1.60 | $1.10Lowest | $2.66 |
| View details | View details | View details |
