Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cerebras Code

cerebras.ai

Post reply on HN
Print view View original

1–10 of 185 posts

Re: Cerebras Code

#2

Post by namanyayg »

I was waiting for more subscription base services to pop up to compete with the influence provider on a commodities level.

I think a lot more companies will follow suit and the competition will make pricing much better for the end user.

congrats on the launch Cerebras team!

Re: Cerebras Code

#3

Post by sophia01 »

My understanding is that the coding agents people use can be modified to plug into any LLM provider's API?

The difference here seems to be that Cerebras does not appear to have Qwen3-Coder through their API! So now there is a crazy fast (and apparently good too?) model that they only provide if you pay the crazy monthly sub?

Re: Cerebras Code

#4

Post by baq »

sophia01 wrote: post #3

My understanding is that the coding agents people use can be modified to plug into any LLM provider's API? The difference here seems to be that Cerebras does not appear to have Qwen3-Coder through their API! So now there is a crazy fast (and apparently good too?) model that they only provide if you pay the crazy monthly sub?

define 'crazy'.

it's two kilotokens per second. that's fast.

Re: Cerebras Code

#5

Post by ttoinou »

baq wrote: post #4
sophia01 wrote: post #3

My understanding is that the coding agents people use can be modified to plug into any LLM provider's API? The difference here seems to be that Cerebras does not appear to have Qwen3-Coder through their API! So now there is a crazy fast (and apparently good too?) model that they only provide if you pay the crazy monthly sub?

define 'crazy'. it's two kilotokens per second. that's fast .

I’d say super fast

Re: Cerebras Code

#6

Post by JackYoustra »

I've been waiting on this for a LONG time. Integration with Cursor when Cerebras released their earlier models was patchy at best, even through openrouter. It's nice to finally see official support, although I'm a bit worried about long-term the time for bash mcp calls ending up dominating.

Still, definitely the right direction!

EDIT: doesn't seem like anything but a first-party api with a monthly plan.

Re: Cerebras Code

#7

Post by ktsakas »

Does it work with claude-code-router? I was getting API errors this week trying to use qwen3 Cerebras through OpenRouter with Claude code router.

Re: Cerebras Code

#8

Post by thanhhaimai »

> running at speeds of up to 2,000 tokens per second, with a 131k-token context window, no proprietary IDE lock-in, and no weekly limits!

I was excited, then I read this:

> Send up to 1,000 messages per day—enough for 3–4 hours of uninterrupted vibe coding.

I don't mind paying for services I use. But it's hard to take this seriously when the first paragraph claim is contradicting the fine prints.

Re: Cerebras Code

#9

Post by pxc »

sophia01 wrote: post #3

My understanding is that the coding agents people use can be modified to plug into any LLM provider's API? The difference here seems to be that Cerebras does not appear to have Qwen3-Coder through their API! So now there is a crazy fast (and apparently good too?) model that they only provide if you pay the crazy monthly sub?

You can still get it pay-as-you-go on OpenRouter, afaict, and the billing section of the Cerebras Cloud account I just created has a section for Qwen3-Coder-480B as well.
Post reply on HN