Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | deepseek-aiDeepSeek-V3Remove × |
|---|---|
| What’s different | DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts… |
| Date | Dec 25, 2024Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $0.256 in / $0.712 out/ 1M tokensDeepInfra · via OpenRouter · all routes ↗deepinfra/fp4/flex · tier=flex · quantization=fp4 |
| Provider endpoints | 6 endpoints → |
Specifications | |
| Context window | 163.8K |
| Max output | 16.4K |
| Parameters | — |
| Tool calling | Supported |
| Structured output | Supported |
| Open weights | Supported |