# Deepseek r1 with cursor **URL:** \ **Category:** Bug Reports\ **Created:** [January 22, 2025, 8:30am UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445 "2025-01-22T08:30:51Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![collapser-AI](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/collapser-ai/32/21375_2.png) [@collapser-AI](https://forum.cursor.com/u/collapser-AI)\ **Post date:** [January 22, 2025, 8:30am UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/1 "2025-01-22T08:30:51Z")
After setting up DeepSeek R1 with Cursor using the OpenAI API, I encountered an issue where it did not function as expected. The system returned an error message that says the “deepseek-reasoner” does not support consecutive user or assistant messages {“error”:{“message”:“deepseek-reasoner does not support successive user or assistant messages (messages[1] and messages[2] in your input). You should interleave the user/assistant messages in the message sequence.”,“type”:“invalid\_request\_error”,“param”:null,“code”:“invalid\_request\_error”}} ---
**Author:** ![lastmjs](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/lastmjs/32/21486_2.png) [@lastmjs](https://forum.cursor.com/u/lastmjs)\ **Post date:** [January 23, 2025, 5:02am UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/3 "2025-01-23T05:02:57Z")
Hey I’ve got deepseek-r1 natively in Cursor now! Go check your models, you might have it there! ---
**Author:** ![collapser-AI](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/collapser-ai/32/21375_2.png) [@collapser-AI](https://forum.cursor.com/u/collapser-AI)\ **Post date:** [January 23, 2025, 6:38am UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/5 "2025-01-23T06:38:38Z")
Thanks. I’ve already tested it, and I can confirm that r1 can be used normally. However, I did find two small problems: 1: The response speed seems to be a little slow, I don’t know why, v3 also has the same problem [if you use the OpenAI API interface to call v3, the response is very fast] 2: The previous use, the phenomenon of disconnected network connection occurred. ---
**Author:** ![Rain](https://avatars.discourse-cdn.com/v4/letter/r/e95f7d/32.png) [@Rain](https://forum.cursor.com/u/Rain)\ **Post date:** [January 23, 2025, 8:31am UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/6 "2025-01-23T08:31:06Z")
According to the forum reply, the cursor does not use the official API of Deepseek, but their partners, which makes the response very slow, but the accuracy and effect are not reduced. I hope it can be optimized. ---
**Author:** ![danperks](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/danperks/32/19087_2.png) [@danperks](https://forum.cursor.com/u/danperks)\ **Post date:** [January 23, 2025, 12:15pm UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/7 "2025-01-23T12:15:40Z")
We are hoping to improve the speed here, but we do use a 3rd party (Fireworks) to run this model to ensure our privacy and security agreements remain in place. ---
**Author:** ![Rain](https://avatars.discourse-cdn.com/v4/letter/r/e95f7d/32.png) [@Rain](https://forum.cursor.com/u/Rain)\ **Post date:** [January 23, 2025, 2:20pm UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/8 "2025-01-23T14:20:40Z")
I used r1 for a day today, the effect is amazing, but the speed is too slow, so I had to switch to cline to use their official API ---
**Author:** ![collapser-AI](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/collapser-ai/32/21375_2.png) [@collapser-AI](https://forum.cursor.com/u/collapser-AI)\ **Post date:** [January 23, 2025, 2:48pm UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/9 "2025-01-23T14:48:25Z")
Okay, I understand. If possible, can you help fix this bug? The faster response of the R1 will make me enjoy using cursor even more. Bonus news: I learned from deepseek folks that r1 doesn’t have a V3-like feature open for the time being. ---
**Author:** ![collapser-AI](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/collapser-ai/32/21375_2.png) [@collapser-AI](https://forum.cursor.com/u/collapser-AI)\ **Post date:** [January 23, 2025, 2:50pm UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/10 "2025-01-23T14:50:52Z")
R1 official API with cline in cursor? ---
**Author:** ![Rain](https://avatars.discourse-cdn.com/v4/letter/r/e95f7d/32.png) [@Rain](https://forum.cursor.com/u/Rain)\ **Post date:** [January 23, 2025, 3:55pm UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/11 "2025-01-23T15:55:30Z")
Yeah, I am forced to use the official cline+deepseek api in the cursor because the rate ---
**Author:** ![ring0jke](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/ring0jke/32/21678_2.png) [@ring0jke](https://forum.cursor.com/u/ring0jke)\ **Post date:** [January 23, 2025, 7:14pm UTC](https://forum.cursor.com/t/deepseek-r1-with-cursor/43445/12 "2025-01-23T19:14:19Z")
Insanely slow R1. it takes 3-4 minutes just to start thinking stage… please expand capacity for R1, now its impossible to use it normally