DeepSeek-R1-0528-Qwen3-8B is a high-performance reasoning model based on the Qwen3 8B Base model, enhanced through the integration of DeepSeek-R1-0528's Chain-of-Thought (CoT) optimization.
https://api.novita.ai/v3/openai/v1/chat/completions| Model | Context | Max out | Pricing |
|---|---|---|---|
| DeepSeek R1 Distill Qwen3 8B 0528 | 128K | 32K | $0.06$0.09 |
| DeepSeek R1 Distill Qwen 14B | 33K | 16K | $0.15$0.15 |
| DeepSeek R1 Distill Qwen 32B | 64K | 32K | $0.3$0.3 |
| DeepSeek R1 0528 | 164K | 33K | $0.7$2.5 |
| DeepSeek R1 Turbo | 64K | 16K | $0.7$2.5 |
| DeepSeek R1 Distill Llama 70B | 8K | 8K | $0.8$0.8 |
| DeepSeek R1 | 64K | 8K | $4$4 |
| DeepSeek R1 | 64K | 16K | $4$4 |
/v1/models/novita/deepseek/deepseek-r1-0528-qwen3-8bDeepSeek-R1-0528-Qwen3-8B is a high-performance reasoning model based on the Qwen3 8B Base model, enhanced through the integration of DeepSeek-R1-0528's Chain-of-Thought (CoT) optimization.