# Together AI

20 Hacker News commenters recommended Together AI and 7 criticized it, November 2025 to November 2026. It was recommended in 9 of 13 months. It meets the Hacker Approved badge rule.

**Verdict:** People recommend it for fast, cheap hosting of open-weight models with data-confidentiality terms. The most common caveat is that it can be pricier than alternatives and sometimes slower.

## Why people recommend it

- Open-weight models hosted on US servers (4 comments): "I’ve mostly settled on using a mixture of open weights models through Together.ai and Fireworks.ai" ([source](https://news.ycombinator.com/item?id=49417855)) "You can use Chinese models hosted on US servers (like a together.ai – there are others)." ([source](https://news.ycombinator.com/item?id=48330143)) "I stick with OpenCode Zen (only US providers) and Together.ai (hosting themselves)." ([source](https://news.ycombinator.com/item?id=48981940))
- Fast token throughput (3 comments): "Together.ai, Baseten, and others have already achieved higher throughput, lower latency, and lower E2E latency" ([source](https://news.ycombinator.com/item?id=50165101)) ""together" provider is fastest (165 t/s at the time of writing) and has ZDR and all" ([source](https://news.ycombinator.com/item?id=49791519)) "I was getting 200-300 tokens/second the other day with Together as my provider" ([source](https://news.ycombinator.com/item?id=50014064))
- Zero data retention and confidentiality (3 comments): "companies like together.ai, fireworks.ai have tons of deals that focus very much on data confidentiality." ([source](https://news.ycombinator.com/item?id=49622578)) ""together" provider is fastest (165 t/s at the time of writing) and has ZDR and all" ([source](https://news.ycombinator.com/item?id=49791519)) "They also get ZDR/session privacy." ([source](https://news.ycombinator.com/item?id=49566355))
- Cheaper than big-lab APIs (2 comments): "offer a wide range of models like gpt oss that are very capable and far cheaper than the models from big 3." ([source](https://news.ycombinator.com/item?id=48435889)) "MiniMax where DeepInfra and Together are much cheaper" ([source](https://news.ycombinator.com/item?id=47358870))

## What people warn about

- Pricier than some alternatives (4 comments): "Together.ai is a good US provider but then it's 15X more expensive" ([source](https://news.ycombinator.com/item?id=48098098)) "then it's 15X more expensive than DeepSeek's Chinese-subsidized pricing" ([source](https://news.ycombinator.com/item?id=48090537)) "fast-but-expensive (Together, Fireworks — you pay for always-on GPUs)" ([source](https://news.ycombinator.com/item?id=47355411))
- Outages and unreliable success rates (2 comments): "they seem fairly unreliable with constant outages or higher than normal latency" ([source](https://news.ycombinator.com/item?id=48200664)) "Together AI has only 71% success rate" ([source](https://news.ycombinator.com/item?id=45844063))

## Alternatives hackers recommend

- [DeepInfra](https://hackerapproved.com/p/deepinfra.md): 36 recommend
- [fal.ai](https://hackerapproved.com/p/fal-ai.md): 19 recommend
- [Neuralwatt](https://hackerapproved.com/p/neuralwatt.md): 18 recommend
- [Baseten](https://hackerapproved.com/p/baseten.md): 15 recommend
- [Replicate](https://hackerapproved.com/p/replicate.md): 13 recommend

## Where to get it

- [Visit the official site](https://www.together.ai/)

## Cite as

Hacker Approved, "Together AI", https://hackerapproved.com/p/together-ai/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).