Richy Chen

Product @FireworksAI_HQ

[Fireworks AI @FireworksAI_HQ]

Reliability shouldn't require reserving GPUs.

Serverless 2.0 is live on Fireworks: one API, 3 serving paths.

→ Standard: elastic default
→ Priority: sheds last under congestion, pricing ~1.5x standard
→ Fast: >100+ tok/s on Kimi K2.6 and GLM 5.1

Get started: https://t.co/yJ6hHgqDE5

[Nathan Tindall @ntindall_]

Excited to launch Composer 2.5 today!

Huge shoutout to the team at @FireworksAI_HQ for being a fantastic partner throughout the process.

[Richy Chen @richychn]

@cloudxdev @FireworksAI_HQ sorry, our billing vendor had a brief outage. it should be good now. please DM me your account id if you still see issues.

[Richy Chen @richychn]

@boristane what tps are you looking for? right now on fireworks, you should see 70-100 tps.

[Fireworks AI @FireworksAI_HQ]

Fireworks Training is now in preview.

You can now full-parameter fine-tune Kimi K2.5 (1T params, 256k context) with custom loss functions (GRPO, DRO, DAPO, or bring your own) on managed infra.

@genspark_ai built their proprietary model stack in four weeks. @vercel hit 93% error-free generation with RFT. @cursor_ai runs their RL rollout fleet on Fireworks.

Full-parameter from 8B to 1T. Multi-LoRA serving. Managed or bring your own training loop.
Your model is your product. Your data is your moat.
https://t.co/kyz7HzihC1

[Richy Chen @richychn]

@Verzach31 @iamcienlim @FireworksAI_HQ we're aware of this bug, sorry about that! we're going to make sure this gets fixed before your card actually gets charged.

[Richy Chen @richychn]

@jamesperkins @BurnedChris @ScriptedAlchemy @FireworksAI_HQ we resolved via discord!

[Richy Chen @richychn]

@rezaul_arif @FireworksAI_HQ which model do you want?

[Qwen @Alibaba_Qwen]

Strategic Partnership Launch:
Qwen 3.6-Plus Debuts on https://t.co/xUfcXNBnK6

Fireworks is known for its proven track record of serving state-of-the-art models at best-in-class performance and cost across the industry.

We're thrilled to announce a landmark collaboration between Alibaba Qwen and Fireworks — bringing Qwen's flagship model to Fireworks' high-performance inference platform.

Qwen3.6-Plus will be soon available on Fireworks AI for inference and fine-tuning, featuring:

● Industry-leading inference performance and cost efficiency powered by Fireworks' optimized serving stack
● Fine-tuning support to customize Qwen3.6-Plus for your specific use cases

Built for scale, engineered for speed. US and global developers: your access is coming soon. Stay tuned！
@FireworksAI_HQ

[Richy Chen @richychn]

@imgggalvin @FireworksAI_HQ really sorry about this. please dm me your account id

[Richy Chen @richychn]

@0xBernard_ we definitely welcome feedback as we build it out more!

[Richy Chen @richychn]

👀

[Vatsal Bajpai @vatsalbajpai_]

Now you can use your @FireworksAI_HQ FirePass
models in Orbital IDE!

It is so fast that the video for inferencing is at 1x, while me setting up is 2x ⚡️

> get the full IDE features for accept/reject
> get full codebase indexing search > get web search + web fetch support
> optimised agentic tools for many MOE models
> no limits or payment needed

Download for Mac here: https://t.co/i4ybv6AjWi

Follow us for more exciting updates @matteraiorg

[Richy Chen @richychn]

@baanditeagle @Zenoware @FireworksAI_HQ @mweinbach @lumendriada during this promotion period, we should not have token limits. please dm me your account id and i can look into what you're hitting.

[Richy Chen @richychn]

@HakodaPrince @FireworksAI_HQ @mweinbach @lumendriada please dm me your account id, and i'll help unblock you.

[Richy Chen @richychn]

@MightyChungus @FireworksAI_HQ really sorry about this - please dm me your account id and i'll take a look

[Richy Chen @richychn]

@0xBernard_ @cjayls @FireworksAI_HQ @mweinbach @lumendriada fire pass is currently an early access promotion. we're letting the community try this out as we build it, but we don't want to overpromise anything.

[Richy Chen @richychn]

@tyler_dot_earth @FireworksAI_HQ yes! fire pass is ZDR

[Richy Chen @richychn]

@sollnikhil @FireworksAI_HQ lots of people like kimi k2.5 for coding. which models are you thinking?

[Richy Chen @richychn]

@salastasius @FireworksAI_HQ @mweinbach @1kartikkabadi1 dm me your account id