Cerebras's banner

Cerebras

@cerebras • 62,588 subscribers

The world's fastest AI inference and training. Try the latest open models at: https://t.co/jREGhLI2nj

Shorts

Google's new fast model 3.5 Flash vs Cerebras

Google's new fast model 3.5 Flash vs Cerebras

144,865 Aufrufe

🟪 Qwen3-235B 2507 Instruct is live on Cerebras 1400 TPS • 131K Context • 230ms TTFT $0.6 | $1.2 per M tokens Try chat: Get API key: Pay-as-you-go via

🟪 Qwen3-235B 2507 Instruct is live on Cerebras 1400 TPS • 131K Context • 230ms TTFT $0.6 | $1.2 per M tokens Try chat: Get API key: Pay-as-you-go via

536,432 Aufrufe

Cerebras Code just got an UPGRADE. It's now powered by GLM 4.6 Pro Plans ($50): 300k ▶️ 1M TPM @ 24M Tokens/day Max Plans ($200): 400k ▶️ 1.5M TPM @ 120M Tokens/day Fastest GLM provider on the planet at 1000 tokens/s and at 131K context. Get yours before we run out 👇

Cerebras Code just got an UPGRADE. It's now powered by GLM 4.6 Pro Plans ($50): 300k ▶️ 1M TPM @ 24M Tokens/day Max Plans ($200): 400k ▶️ 1.5M TPM @ 120M Tokens/day Fastest GLM provider on the planet at 1000 tokens/s and at 131K context. Get yours before we run out 👇

177,904 Aufrufe

No more waitlist – Cerebras inference API is open to all! 1M free tokens/day 20x GPU speed Reasoning in ~1 second It's time to build!

No more waitlist – Cerebras inference API is open to all! 1M free tokens/day 20x GPU speed Reasoning in ~1 second It's time to build!

108,466 Aufrufe

Cerebras Code Plans are open for business and massively upgraded. Pro Plans ($50): 165k▶️300k TPM @ 24M Tokens/day Max Plans ($200): 300k▶️400k TPM @ 120M Tokens/day More vibing, more tokens. Keep sending us feedback!

Cerebras Code Plans are open for business and massively upgraded. Pro Plans ($50): 165k▶️300k TPM @ 24M Tokens/day Max Plans ($200): 300k▶️400k TPM @ 120M Tokens/day More vibing, more tokens. Keep sending us feedback!

51,711 Aufrufe

Perplexity Pro is Now Powered by Cerebras. Perplexity Sonar, now running on Cerebras Inference, delivers answers at an unprecedented 1,200 tokens/s – 10x faster than comparable models.

Perplexity Pro is Now Powered by Cerebras. Perplexity Sonar, now running on Cerebras Inference, delivers answers at an unprecedented 1,200 tokens/s – 10x faster than comparable models.

68,007 Aufrufe

We built Death by Diet Coke in less than 30 seconds using Cerebras Code Pro, where you get higher rate limits and more power for Qwen3-Coder. We are opening the same number of Cerebras Code Pro/Max plans as diet coke cans in the office. First come, first serve.

We built Death by Diet Coke in less than 30 seconds using Cerebras Code Pro, where you get higher rate limits and more power for Qwen3-Coder. We are opening the same number of Cerebras Code Pro/Max plans as diet coke cans in the office. First come, first serve.

47,752 Aufrufe

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

Gemma 4 31B is now available in Public Preview on Cerebras. Our first multimodal model runs at over 1,800 tokens/s for ultra-fast image and text workflows. Give it a try:

269,017 Aufrufe • vor 19 Tagen

NVIDIA paid $20B for Groq. AWS partnered with Cerebras for the same purpose. A quick breakdown of why disaggregated inference is the next thing in AI infrastructure.

NVIDIA paid $20B for Groq. AWS partnered with Cerebras for the same purpose. A quick breakdown of why disaggregated inference is the next thing in AI infrastructure.

383,060 Aufrufe • vor 1 Monat

Right now, when you send a query to an LLM, it gets decrypted on the server. The LLM sees your data in plain text. Prof. Ajay Joshi (BU, CipherSonic AI ) on fully homomorphic encryption, which may be key for the future of AI privacy: how we can compute on data without ever decrypting it. The catch: it's a brutally memory-bound workload. Exactly the bottleneck wafer-scale was built to solve.

Right now, when you send a query to an LLM, it gets decrypted on the server. The LLM sees your data in plain text. Prof. Ajay Joshi (BU, CipherSonic AI ) on fully homomorphic encryption, which may be key for the future of AI privacy: how we can compute on data without ever decrypting it. The catch: it's a brutally memory-bound workload. Exactly the bottleneck wafer-scale was built to solve.

293,415 Aufrufe • vor 29 Tagen

We gave two agents the same task: “Find images matching this description.” Both use Gemma 4 31B. One runs on Cerebras. The other runs on GPUs. You can see the difference. Speed changes the product experience. What would you build if you didn't have to wait?

We gave two agents the same task: “Find images matching this description.” Both use Gemma 4 31B. One runs on Cerebras. The other runs on GPUs. You can see the difference. Speed changes the product experience. What would you build if you didn't have to wait?

141,858 Aufrufe • vor 17 Tagen

GLM 4.7 is one of the strongest open-source coding models available—but most developers aren't prompting it correctly. We put together 10 rules to help you get the most out of it: - Front-load instructions (it has a strong recency bias) - Use firm language: "must" and "strictly" > soft suggestions - Break complex tasks into smaller steps - Disable reasoning for simple tasks, enable it for hard ones - Use critic agents for code review, QA, and validation - Pair it with a frontier model for the hardest 10% of workloads - and more… GLM 4.7 hits 96% on Tau² Bench and 86% on GPQA Diamond. At 1,500 tokens/sec on Cerebras, it's 20x faster than closed-source alternatives on GPUs.

GLM 4.7 is one of the strongest open-source coding models available—but most developers aren't prompting it correctly. We put together 10 rules to help you get the most out of it: - Front-load instructions (it has a strong recency bias) - Use firm language: "must" and "strictly" > soft suggestions - Break complex tasks into smaller steps - Disable reasoning for simple tasks, enable it for hard ones - Use critic agents for code review, QA, and validation - Pair it with a frontier model for the hardest 10% of workloads - and more… GLM 4.7 hits 96% on Tau² Bench and 86% on GPQA Diamond. At 1,500 tokens/sec on Cerebras, it's 20x faster than closed-source alternatives on GPUs.

633,658 Aufrufe • vor 5 Monaten

Multimodal reasoning has a latency problem. More video frames leads to more waiting. We built Damage Scout with Gemma 4 on Cerebras, running at over 2,300 toks/s, to show what fast multimodal inference unlocks. Damage Scout samples frames from a rental car walkaround, sends them to Gemma 4, gets back structured findings and box coordinates, then renders an annotated damage report in under 6 seconds. Same task. Same frames. A complete different experience powered by Cerebras ⚡️

Multimodal reasoning has a latency problem. More video frames leads to more waiting. We built Damage Scout with Gemma 4 on Cerebras, running at over 2,300 toks/s, to show what fast multimodal inference unlocks. Damage Scout samples frames from a rental car walkaround, sends them to Gemma 4, gets back structured findings and box coordinates, then renders an annotated damage report in under 6 seconds. Same task. Same frames. A complete different experience powered by Cerebras ⚡️

30,493 Aufrufe • vor 8 Tagen

OpenAI Codex-Spark powered by Cerebras You can now just build things faster—at 1,000 tokens/s.

OpenAI Codex-Spark powered by Cerebras You can now just build things faster—at 1,000 tokens/s.

287,547 Aufrufe • vor 5 Monaten

After 9 years at NVIDIA, James Wang left and joined Cerebras. In this Big Chip Club episode, James Wang breaks down the bottlenecks of NVIDIA GPUs, and what's keeping them OUT OF first place... Drop your follow-up questions below 👇

After 9 years at NVIDIA, James Wang left and joined Cerebras. In this Big Chip Club episode, James Wang breaks down the bottlenecks of NVIDIA GPUs, and what's keeping them OUT OF first place... Drop your follow-up questions below 👇

411,916 Aufrufe • vor 8 Monaten

Some of our top customers are still choosing Llama 3.1 8B. For a while, we jumped to whatever hottest, latest model was taking up our twitter feed. 🙈 But as we are quickly realizing, to create a SOTA product, you need a model that fits your exact use case. Here’s what our customers tell us: > a lot of the legwork is actually around prompting > there’s an art to selecting and combining multiple models > benchmarks only show part of the picture. you have to understand the unique quirks of each model. Especially as model releases become more and more frequent, we need a clear way to evaluate new models. We have to break free of the naive trend to migrate to the ‘latest and greatest’. And you can easily achieve this using tools like Cerebras and Braintrust to swap models safely (without breaking production).

Some of our top customers are still choosing Llama 3.1 8B. For a while, we jumped to whatever hottest, latest model was taking up our twitter feed. 🙈 But as we are quickly realizing, to create a SOTA product, you need a model that fits your exact use case. Here’s what our customers tell us: > a lot of the legwork is actually around prompting > there’s an art to selecting and combining multiple models > benchmarks only show part of the picture. you have to understand the unique quirks of each model. Especially as model releases become more and more frequent, we need a clear way to evaluate new models. We have to break free of the naive trend to migrate to the ‘latest and greatest’. And you can easily achieve this using tools like Cerebras and Braintrust to swap models safely (without breaking production).

346,446 Aufrufe • vor 7 Monaten

Cerebras Code: 20x faster than Claude, 1x the price Today we are launching two monthly coding plans: ➡️Cerebras Code Pro: $50/m – for indie developers ➡️Cerebras Code Max: $200/m – for power users with 5x rate limits Both plans get: Qwen3-Coder at 2,000 tokens/s, 131K context, and no weekly limits. Sign up now:

Cerebras Code: 20x faster than Claude, 1x the price Today we are launching two monthly coding plans: ➡️Cerebras Code Pro: $50/m – for indie developers ➡️Cerebras Code Max: $200/m – for power users with 5x rate limits Both plans get: Qwen3-Coder at 2,000 tokens/s, 131K context, and no weekly limits. Sign up now:

461,227 Aufrufe • vor 11 Monaten

🎁 We're giving away 5 Windsurf plans ($250 credit each)! Try SWE-1.6 — Cognition’s latest fast and intelligent agentic coding model, powered by Cerebras. In a side-by-side with Claude, the speed difference is clear. More iterations, faster fixes, better code. 💬Comment why you want access to enter. Five winners will be selected at random within 48 hours.

🎁 We're giving away 5 Windsurf plans ($250 credit each)! Try SWE-1.6 — Cognition’s latest fast and intelligent agentic coding model, powered by Cerebras. In a side-by-side with Claude, the speed difference is clear. More iterations, faster fixes, better code. 💬Comment why you want access to enter. Five winners will be selected at random within 48 hours.

104,937 Aufrufe • vor 2 Monaten

"The hardware lottery got worse." Six years after Sara Hooker's landmark essay, she's even more convinced that our current chips are constraining which AI ideas succeed — and which never get a chance.

"The hardware lottery got worse." Six years after Sara Hooker's landmark essay, she's even more convinced that our current chips are constraining which AI ideas succeed — and which never get a chance.

18,564 Aufrufe • vor 12 Tagen

Everyone talks about our hardware @Cerebras. Few notice the software. Ryan Loney breaks down the hidden optimizations powering 20× faster LLM inference than GPUs, speculative decoding, token reuse, and why we’re just getting started. Watch the full story here

Everyone talks about our hardware @Cerebras. Few notice the software. Ryan Loney breaks down the hidden optimizations powering 20× faster LLM inference than GPUs, speculative decoding, token reuse, and why we’re just getting started. Watch the full story here

222,816 Aufrufe • vor 6 Monaten

Introducing Cerebras Inference ‣ Llama3.1-70B at 450 tokens/s – 20x faster than GPUs ‣ 60c per M tokens – a fifth the price of hyperscalers ‣ Full 16-bit precision for full model accuracy ‣ Generous rate limits for devs Try now:

Introducing Cerebras Inference ‣ Llama3.1-70B at 450 tokens/s – 20x faster than GPUs ‣ 60c per M tokens – a fifth the price of hyperscalers ‣ Full 16-bit precision for full model accuracy ‣ Generous rate limits for devs Try now:

706,706 Aufrufe • vor 1 Jahr

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

In pick the best model > improve your prompts > catch bugs with Braintrust and Cerebras inference. Avoid the AI deleting your entire codebase this halloween and remember, our free tier gets you 1M+ free toks/day per model.

299,029 Aufrufe • vor 9 Monaten

Let's talk about MoE: 🔶 How many experts should you use? 🔶 How does dynamic routing actually behave in production? 🔶 How do you debug a model that won’t train? 🔶 What does 8x7B actually mean for memory and compute? 🔶 What hardware optimizations matter for sparse models? Mixture of Experts (MoE) is changing how the biggest AI models are built — but it’s still hard to get right. That's why we are launching a new MoE 101 series, led by Daria Soboleva to bridge the gap between theory and practice. Dive in to our MoE guide:

Let's talk about MoE: 🔶 How many experts should you use? 🔶 How does dynamic routing actually behave in production? 🔶 How do you debug a model that won’t train? 🔶 What does 8x7B actually mean for memory and compute? 🔶 What hardware optimizations matter for sparse models? Mixture of Experts (MoE) is changing how the biggest AI models are built — but it’s still hard to get right. That's why we are launching a new MoE 101 series, led by Daria Soboleva to bridge the gap between theory and practice. Dive in to our MoE guide:

345,732 Aufrufe • vor 1 Jahr

"I used a billion tokens this week. I'm not even in the top 100 Codex users at OpenAI." We sat down with jason (creator of Instructor, now on OpenAI's Developer Experience team) to talk about how zero-latency inference is changing the way engineers work.

"I used a billion tokens this week. I'm not even in the top 100 Codex users at OpenAI." We sat down with jason (creator of Instructor, now on OpenAI's Developer Experience team) to talk about how zero-latency inference is changing the way engineers work.

93,023 Aufrufe • vor 3 Monaten

GLM-4.7 from Z.ai is live on Cerebras! - Frontier intelligence for coding, tool-driven agents, and multi-turn reasoning - Record coding speed: ~1,000 tokens per second (up to 1,700 TPS for other uses) - Strong price-performance: ~10x higher than Sonnet 4.5

GLM-4.7 from Z.ai is live on Cerebras! - Frontier intelligence for coding, tool-driven agents, and multi-turn reasoning - Record coding speed: ~1,000 tokens per second (up to 1,700 TPS for other uses) - Strong price-performance: ~10x higher than Sonnet 4.5

134,887 Aufrufe • vor 6 Monaten

Fully homomorphic encryption was invented in the 1980s. Why wasn't it adopted sooner? A 100,000x slowdown, driven by memory boundedness. Ajay Joshi from CipherSonic AI explains how his team got it down to less than 2x. (if this pattern sounds familar... LLM inference is memory-bound too. It's why wafer-scale exists.)

Fully homomorphic encryption was invented in the 1980s. Why wasn't it adopted sooner? A 100,000x slowdown, driven by memory boundedness. Ajay Joshi from CipherSonic AI explains how his team got it down to less than 2x. (if this pattern sounds familar... LLM inference is memory-bound too. It's why wafer-scale exists.)

57,654 Aufrufe • vor 2 Monaten

🚨 Cerebras Inference is now 3x faster: Llama3.1-70B just broke 2,100 tokens/s - 16x faster than the fastest GPU solution - 8x faster than GPUs running Llama *3B* - It's like the perf of a new hardware generation in a single software release Available now at

🚨 Cerebras Inference is now 3x faster: Llama3.1-70B just broke 2,100 tokens/s - 16x faster than the fastest GPU solution - 8x faster than GPUs running Llama 3B - It's like the perf of a new hardware generation in a single software release Available now at

236,067 Aufrufe • vor 1 Jahr