Loading...
Loading...
DeepSeek R1 — open-source reasoning model with chain-of-thought, matching o1 performance at 95% lower API cost.
$0.180
per 1M input tokens
—
top score across benchmarks
9
APIs serving this model
128K
max token window
Looking for alternatives?
Find cheaper or faster models in the same class.
See DeepSeek R1 alternatives →deepseek-ai DeepSeek-R1-Distill-Qwen-32B | Free* | — | — | — |
deepseek-ai DeepSeek R1 Distill Qwen 1.5B | $0.180 | $0.180 | 256ms | 131k |
tngtech TNG: DeepSeek R1T2 Chimera | $0.300 | $1.100 | — | 164k |
deepseek-ai deepseek-r1-distill-qwen-32b | $0.497 | $4.881 | 372ms | 80k |
deepseek-ai DeepSeek R1 Distill Qwen 14B | $1.600 | $1.600 | 253ms | 131k |
deepseek-ai DeepSeek R1 Distill Llama 70B | $2.000 | $2.000 | 255ms | 131k |
deepseek-ai DeepSeek R1 0528 NVFP4 | $3.000 | $7.000 | 254ms | 164k |
* Free tier or self-hosted option available. Compute costs apply for self-hosting.