Top all-time · #1925
Fireworks AI
Company blog · fireworks.ai/blogaiprogramming
Fireworks AI is the company blog at fireworks.ai, writing about ai and programming. Since 2024, 39 different Hacker News readers have linked it 58 times, most often “Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA”. No feed was found, so read it on the site itself.
Rarely recommended · 0 of 31 sampled comments recommend it?
Why HN links it
HN readers mostly mention Fireworks as a hosted inference provider for open-weight models like DeepSeek, Kimi and Llama, and sometimes link its blog posts on pricing, fine-tuning and model launches.
Summarised by Claude from a sample of 31 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Fireworks’ state of the art training and inference platform take you beyond the frontier, transforming open models into your specialized intelligence.
Most-linked posts?
- Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA4 people · 4 mentions · first linked 2026-07-21
- /3 people · 3 mentions · first linked 2025-12-27
- /3 people · 3 mentions · first linked 2024-06-07
- FireFunction V1 – GPT-4-level function calling model – 4x faster, open weights2 people · 2 mentions · first linked 2024-02-22
- The Benchmark Gap: What It Takes to Ship Kimi K2.52 people · 2 mentions · first linked 2026-02-16
- /models/fireworks/deepseek-r12 people · 2 mentions · first linked 2025-01-26
- /blog/cursor2 people · 2 mentions · first linked 2024-11-05
- GPUs on-demand: Not serverless, not reserved, but some third thing2 people · 2 mentions · first linked 2024-06-07
- Ember-12 people · 2 mentions · first linked 2026-09-27
- How Fireworks evaluates quantization precisely and interpretably2 people · 2 mentions · first linked 2024-08-03
What Hacker News says?
They're using it via fireworks.ai, which is the 685B model. https://fireworks.ai/models/fireworks/deepseek-r1
Comment linking /models/fireworks/deepseek-r1
on “DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL”Submitted Ember-1 as a story · 589 points
HN discussionYou have NO IDEA what you're talking about. You are clueless. Deepseek v4.1 flash is an open weights model. You can run it on your own hardware. You have no idea how my companies gets access to it. A very cursory Google search would reveal to you that there are many enterprise grade LLM providers that host this model on US soil with SOC2 protections. Like: https://fireworks.ai/ Try not to talk about subjects you hav…
Comment linking /
on “Why isn't the industry freaking out about DeepSeek 4.1 Flash?”Submitted Kimi K3 Is Competitive with Fable; Kimi K3 and Fable Is SoTA as a story · 37 points
HN discussionFireworks supports this model serverless for $1.20 per million tokens. https://fireworks.ai/models/fireworks/deepseek-v3p2
Comment linking /models/fireworks/deepseek-v3p2
on “DeepSeek-v3.2: Pushing the frontier of open large language models [pdf]”Submitted FireAttention V3: Enabling AMD as a Viable Alternative for GPU Inference as a story · 20 points
HN discussionNo need to use a chinese provider, in case that's an issue for you. https://fireworks.ai provides this model for an ok price.
Comment linking /
on “DeepSeek-v4.1-Flash-1017”Submitted Fireworks F1: A Breakthrough in Complex Reasoning with Compound AI as a story · 17 points
HN discussionyup, we use Fireworks.ai, and American company with ZDR Their new Ember-1 model is pretty good, fine-tune of Kimi3 with way less thinking Does this make it an American model or is it still Chinese? Does it matter? https://fireworks.ai/blog/ember-1
Comment linking /blog/ember-1
on “Sonnet 5.5”Submitted FireFunction V1 – GPT-4-level function calling model – 4x faster, open weights as a story · 7 points
HN discussionmeta.ai is inaccessible in a large portion of world territories, but the Llama 3.1 70B and 405B are also available in https://hf.co/chat Additionally, all Llama 3.1 models are available in https://api.together.ai/playground/chat/meta-llama/Meta-Llam... and in https://fireworks.ai/models/fireworks/llama-v3p1-405b-instru... by logging in.
Comment linking /models/fireworks/llama-v3p1-405b-instruct
on “Large Enough”Submitted LLM Eval Driven Development with Claude Code as a story · 4 points
HN discussionit's not exactly the same, the model stills "weighs" the same here, it does less work, it's more like driving half as far but still paying the same total cost this being said, K3 and E1 models are priced the same at $3.00 / $0.30 / $15.00 https://fireworks.ai/models/fireworks/kimi-k3 https://fireworks.ai/models/fireworks/ember-1
Comment linking /models/fireworks/ember-1
on “Ember-1”Submitted Phylo brings frontier AI to more scientists with open models on Fireworks as a story · 3 points
HN discussionThe costs for OpenAI and Google aren't public, but if you look at the open-source models, inference is very cheap: for example, you can generally beat the public serverless prices by a factor of ~2 by using dedicated GPUs [1], and given that a 70b model costs about $1/million tokens serverless — and tend to perform similarly on benchmarks to 4o — OpenAI is most likely getting very fat profit margins at $2.50/million…
Comment linking /blog/why-gpus-on-demand
on “Operator research preview”Submitted Fireworks – Announcing our Series D and $1B ARR as a story · 3 points
HN discussionThis is stretching my own knowledge, so if someone else knowledgeable wants to take a stab here I would appreciate a response as well! Before doing that, I would start basic. Pull llama3 and see what it does with your prompts. You may be surprised how much is already in there and just not need to involve your own data at all. If that doesn’t work, check HuggingFace to see if someone has already made a model/fine tun…
Comment linking /blog/firefunction-v1-gpt-4-level-function-calling
on “IBM Granite: A Family of Open Foundation Models for Code Intelligence”Submitted Matching frontier performance through training and harness engineering as a story · 2 points
HN discussionFireworks does. It is frustrating that AWS/Google/Azure do not. https://fireworks.ai/docs/structured-responses/structured-ou...
Comment linking /docs/structured-responses/structured-output-grammar-based
on “Sampling and structured outputs in LLMs”Submitted DeepSeek V4 Pro: Validating Frontier Models for Production as a story · 2 points
HN discussionFor anyone more curious about how this works, Fireworks wrote a blog post about it last year (I think): https://fireworks.ai/blog/cursor
Comment linking /blog/cursor
on “Launch HN: Morph (YC S23) – Apply AI code edits at 4,500 tokens/sec”Submitted How we fixed prompt injection for all models on Fireworks as a story · 2 points
HN discussionDeepSeek V3 is easily the best cost / performance non-reasoning model on the market but accessing it via API is not straightforward -- at least for people who want their model hosted in the US. For the layperson OpenAI / Anthropic are much more accessible. Some of OpenRouter's [0][1] providers seem bunk; their version is corrupted. Occasionally just get mangled outputs. Fireworks [2] is my best experience so far: th…
Comment linking /models/fireworks/deepseek-v3
on “Anthropic raises $3.5B at $61.5B valuation”Submitted Why Building Mega Clusters Is Wrong as a story · 2 points
HN discussionMe too. I use now https://fireworks.ai/ for vision models to test.
Comment linking /
on “Dragonfly: A large vision-language model with multi-resolution zoom”Submitted The Benchmark Gap: What It Takes to Ship Kimi K2.5 as a story · 2 points
HN discussionThe current panic is happening precisely because Chinese open weight models like Kimi and Qwen are demonstrably competitive with SotA models like Fable, but far cheaper. https://fireworks.ai/blog/kimik3-fable
Comment linking /blog/kimik3-fable
on “Startup founders urge Trump not to shut off Chinese open weight AI”Submitted How Fireworks evaluates quantization precisely and interpretably as a story · 2 points
HN discussionFireworks will serve them for $1.74 / $0.14 / $3.48. That's input / cached input / output. https://fireworks.ai/models/deepseek-ai/deepseek-v4-pro . Call it about a third the price of Sonnet. Not nearly as cheap as the Chinese infra but still pretty cheap.
Comment linking /models/deepseek-ai/deepseek-v4-pro
on “Claude Opus 4.8”Submitted Optimizing MiniMax M3 Sparse Attention on Nvidia Blackwell as a story · 1 points
HN discussion
