UberLLM serves DeepSeek models (V3.2, R1, V4) at the cheapest healthy seller — often just a few cents per million tokens — through one OpenAI-compatible key. UberLLM gives you one OpenAI-compatible API key and base URL for every major model, routing every request to the cheapest healthy seller for that model and billing the price shown, with UberLLM's 10% fee already included.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| DeepSeek V4.1 Flash | $0.0004 | $0.0009 |
| DeepSeek V4 Flash 0731 | $0.0010 | $0.0020 |
| DeepSeek V4 Pro | $0.0011 | $0.0022 |
| DeepSeek V3.2 | $0.0029 | $0.0043 |
| DeepSeek V4 Flash | $0.0040 | $0.0080 |
| DeepSeek V3.1 | $0.0027 | $0.0103 |
| DeepSeek V4.1 Flash 1017 | $0.0131 | $0.0523 |
| DeepSeek V4 Pro 0813 | $0.0336 | $0.1008 |
| DeepSeek V4 Flash E2EE | $0.1001 | $0.2051 |
| DeepSeek V4 Flash (Morpheus Web) | $0.1253 | $0.2580 |
| DeepSeek V4 Flash 0731 Fast | $0.1925 | $0.3850 |
| DeepSeek V4 Pro (Morpheus Web) | $1.28 | $2.80 |
Live prices via UberLLM · full pricing table →
DeepSeek models are among the cheapest — commonly a few cents per million tokens via UberLLM, which routes to the lowest-cost healthy seller.