Back

DeepSeek: R1 (free)

DeepSeek
Input: text
Output: text
Released: Jan 20, 2025Updated: May 2, 2025

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.

Fully open-source model & technical report.

MIT licensed: Distill & commercialize freely!

163,840 Token Context

Process and analyze large documents and conversations.

Hybrid Reasoning

Choose between rapid responses and extended, step-by-step processing for complex tasks.

Advanced Coding

Improved capabilities in front-end development and full-stack updates.

Agentic Workflows

Autonomously navigate multi-step processes with improved reliability.

Available On

ProviderModel IDContextMax OutputInput CostOutput CostThroughputLatency
DeepInfradeepInfra164K164K$0.50/M$2.18/M44.4 t/s565 ms
inference.netinferenceNet128K33K$0.50/M$3.00/M22.8 t/s1253 ms
Lambdalambda164K164K$0.54/M$2.18/M37.5 t/s694 ms
NovitaAInovitaAi64K16K$0.70/M$2.50/M27.0 t/s1265 ms
Nebius AI StudionebiusAiStudio164K-$0.80/M$2.40/M27.3 t/s782 ms
DeepInfra TurbodeepInfraTurbo33K-$1.00/M$3.00/M130.7 t/s468 ms
kluster.aiklusterAi164K164K$1.75/M$5.00/M33.2 t/s1324 ms
Parasailparasail131K131K$1.95/M$5.00/M57.7 t/s671 ms
Nebius FastnebiusFast164K-$2.00/M$6.00/M49.7 t/s788 ms
CentMLcentMl131K131K$2.99/M$2.99/M57.5 t/s980 ms
Togethertogether164K33K$3.00/M$7.00/M47.8 t/s1547 ms
Friendlifriendli164K164K$3.00/M$7.00/M61.5 t/s899 ms
Fireworksfireworks164K-$3.00/M$8.00/M56.5 t/s649 ms
SambaNovasambaNova33K16K$5.00/M$7.00/M115.0 t/s4731 ms
Minimaxminimax64K64K$0.55/M$2.19/M18.5 t/s2507 ms
DeepSeekdeepSeek64K8K$0.55/M$2.19/M22.2 t/s4188 ms
Azureazure164K4K$1.48/M$5.94/M85.3 t/s1685 ms
Featherlessfeatherless33K4K$6.50/M$8.00/M13.7 t/s1874 ms
Standard Pricing

Do Work. With AI.