Together AI
Hacker ApprovedRanked 3 of 14 inference providers by recommenders
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.
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.
27 people gave an opinion
- recommend it
- 20
- criticize it
- 7
- approval share
- 74%
Recommended in 9 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: recommended
- March 2026: recommended
- April 2026: recommended
- May 2026: recommended
- June 2026: recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it carries the badge
- 20 people recommend itNeeds 10 or more, met.
- 2.9 recommenders for every criticNeeds 2 to 1 or better, met.
- Recommended in 9 of 13 monthsNeeds 4 or more, met.
The same three rules apply to every product, and the badge can’t be bought. How the badge works
What people say about it
The reasons people give, with the number of comments that give each one. Open a reason to read what they said.
Why people recommend it
Each mark is one comment
Open-weight models hosted on US servers
“I’ve mostly settled on using a mixture of open weights models through Together.ai and Fireworks.ai”
Comment from 24 Aug 2026 in “Anthropic's best AI model struggles to attract users as cheaper tools thrive” “You can use Chinese models hosted on US servers (like a together.ai – there are others).”
Comment from 29 May 2026 in “DeepSeek Slashes AI Costs to Cents” “I stick with OpenCode Zen (only US providers) and Together.ai (hosting themselves).”
Comment from 20 Jul 2026 in “American AI is locked down and proprietary. It's losing” - Comment from 23 Aug 2026 in “GLM-5.3 (open-weight) beat Anthropic/OpenAI models – for 1/5 the cost”
Fast token throughput
“Together.ai, Baseten, and others have already achieved higher throughput, lower latency, and lower E2E latency”
Comment from 20 Oct 2026 in “DeepInfer: High-performance inference framework for DeepSeek models” “"together" provider is fastest (165 t/s at the time of writing) and has ZDR and all”
Comment from 21 Sep 2026 in “Grok 4.7” “I was getting 200-300 tokens/second the other day with Together as my provider”
Comment from 8 Oct 2026 in “Why isn't the industry freaking out about DeepSeek 4.1 Flash?” Zero data retention and confidentiality
“companies like together.ai, fireworks.ai have tons of deals that focus very much on data confidentiality.”
Comment from 9 Sep 2026 in “Navier-Stokes – Tristan Buckmaster [pdf]” “"together" provider is fastest (165 t/s at the time of writing) and has ZDR and all”
Comment from 21 Sep 2026 in “Grok 4.7” “They also get ZDR/session privacy.”
Comment from 4 Sep 2026 in “Pause OpenAI Now” Cheaper than big-lab APIs
“offer a wide range of models like gpt oss that are very capable and far cheaper than the models from big 3.”
Comment from 7 Jun 2026 in “The OnlyFans Economy of American AI” “MiniMax where DeepInfra and Together are much cheaper”
Comment from 12 Mar 2026 in “IonRouter (YC W26) – High throughput, low cost inference”
What people warn about
Each mark is one comment
Pricier than some alternatives
“Together.ai is a good US provider but then it's 15X more expensive”
Comment from 11 May 2026 in “Gemini API File Search is now multimodal” “then it's 15X more expensive than DeepSeek's Chinese-subsidized pricing”
Comment from 11 May 2026 in “Gemini API File Search is now multimodal” “fast-but-expensive (Together, Fireworks — you pay for always-on GPUs)”
Comment from 12 Mar 2026 in “IonRouter (YC W26) – High throughput, low cost inference” - Comment from 14 Jan 2026 in “VLLM Large Scale Serving: DeepSeek 2.2k Tok/S/H200 with Wide-EP”
Outages and unreliable success rates
“they seem fairly unreliable with constant outages or higher than normal latency”
Comment from 19 May 2026 in “Gemini 3.5: frontier intelligence with action” “Together AI has only 71% success rate”
Comment from 7 Nov 2025 in “Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model”
Other inference providers people recommend
The four most recommended other inference providers, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.
| Product | Recommend | Criticize | Approval | Months | Owned | Badge |
|---|---|---|---|---|---|---|
| Fireworks AI | 67 | 19 | 78% | 11 | — | Approved |
| DeepInfra | 36 | 11 | 77% | 11 | — | Approved |
| Together AIThis page | 20 | 7 | 74% | 9 | — | Approved |
| fal.ai | 19 | 7 | 73% | 8 | — | Approved |
| Neuralwatt | 18 | 1 | 95% | 7 | — | Approved |
What people said
25 of the 28 comments that mention it, newest first. Each links to the original comment.
“the inference from together.ai feels like it might be better (not quantified; just vibes)”
“Together.ai, Baseten, and others have already achieved higher throughput, lower latency, and lower E2E latency”
“IMO, together > fireworks > deepinfra.”
“I was getting 200-300 tokens/second the other day with Together as my provider”
“but together doesn't, so they are likely using fp4”
“one of the providers with "blind" vision models”
“"together" provider is fastest (165 t/s at the time of writing) and has ZDR and all”
“The provider's middleware also plays a role.”
“For truly production use cases, use Novita, Fireworks, Toghether or something of the sort.”
“companies like together.ai, fireworks.ai have tons of deals that focus very much on data confidentiality.”
“They also get ZDR/session privacy.”
“I’ve mostly settled on using a mixture of open weights models through Together.ai and Fireworks.ai”
“You can run them on the Together AIs or Firework AIs of this world.”
“I stick with OpenCode Zen (only US providers) and Together.ai (hosting themselves).”
“offer a wide range of models like gpt oss that are very capable and far cheaper than the models from big 3.”
“You can use Chinese models hosted on US servers (like a together.ai – there are others).”
“they seem fairly unreliable with constant outages or higher than normal latency”
“Together.ai is a good US provider but then it's 15X more expensive”
“then it's 15X more expensive than DeepSeek's Chinese-subsidized pricing”
“OpenRouter, Together, Anyscale”
“MiniMax where DeepInfra and Together are much cheaper”
“fast-but-expensive (Together, Fireworks — you pay for always-on GPUs)”
“Together AI is cheap but slower”
“Together AI charges whopping $7/mil output tokens for R1”
“Together AI has only 71% success rate”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.