Qwen 3.8 27B available on Cerebras at 1500 tokens/s

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by gardnr on Thursday September 03, 2026 @02:37PM (#49554591)

I used their Coding Plan for a few months. It is genuinely difficult to keep up with the models. The output is so fast. Qwen 3.8 27B is likely one of the strongest models they've hosted so far.

Edit: it looks like this is only available on a API token pricing. Does anyone know if they have rolled out prompt caching yet? It used to get pretty expensive for agentic coding tasks with no prompt caching.

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by jasongill on Thursday September 03, 2026 @02:46PM (#49554753)

It appears that they do support Prompt Caching: https://inference-docs.cerebras.ai/capabilities/prompt-cachi...

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by the_duke on Thursday September 03, 2026 @03:10PM (#49555123)

It doesn't reduce the price though.

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by jasongill on Friday September 04, 2026 @07:59AM (#49563391)

Good catch, I guess I got lost in the marketing speak of the page!

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by abtinf on Thursday September 03, 2026 @03:08PM (#49555094)

> How are cached tokens priced?

> There is no additional fee for using prompt caching. Input tokens, whether served from the cache or processed fresh, are billed at the standard input token rate for the respective model.

Well, talk about flipping the narrative.

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by Barbing on Thursday September 03, 2026 @03:17PM (#49555242)

heh

Is there a speed increase or is that purely marketing spin on “we might cache on our end but no discount for you”?

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by lostmsu on Thursday September 03, 2026 @03:39PM (#49555612)

Pure marketing.

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by eli on Thursday September 03, 2026 @03:04PM (#49555028)

Strongest model that they host on the public endpoint. They do a super fast version of GPT 5.6 Sol for OpenAI and have bigger open models on dedicated endpoints.

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by altertable on Thursday September 03, 2026 @02:40PM (#49554630)

Agreed, but in our SAAS I can tell some UX will sky-rocket to next level with this

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by singpolyma3 on Thursday September 03, 2026 @03:04PM (#49555036)

The coding plan is gone now right?

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by gardnr on Thursday September 03, 2026 @03:20PM (#49555281)

Last time I got one, I had to log into a Discord server and wait for "the drop" and IIRC Daniel Kim was giving them out based on who was there at the time. They were gone in less than a minute. This was ~8 months ago.

[ Parent | on HN ]

Re:Qwen 3.8 27B available on Cerebras at 1500 tokens/s by cute_boi on Thursday September 03, 2026 @02:47PM (#49554766)

i believe they used to have monthly plan, what happened to that?

[ Parent | on HN ]