StarSeaAPI
DeepSeek
Open-weight frontier models with a focus on reasoning and cost efficiency
DeepSeek models are the default choice for high-volume workloads: strong reasoning, long context and a price point that makes them viable as an always-on backbone. On StarSeaAPI every DeepSeek variant is served through multiple independent upstream routes, so a single provider incident does not take the model offline.
Models (5)
| Models | Input $/M | Output $/M | Intelligence index | Coding index |
|---|---|---|---|---|
| deepseek-v4-flash | $0.15 | $0.61 | 40.8 | 69.1 |
| deepseek-v4-flash-0731 | $0.15 | $0.61 | — | — |
| deepseek-v4.1-flash | $0.15 | $0.61 | — | — |
| deepseek-v4-pro | $0.68 | $2.05 | 42.1 | 68.8 |
| deepseek-v4-pro-0813 | $0.68 | $2.05 | — | — |
Prices are per 1M tokens in USD · ¥6.6 = $1