Together AI
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Jan 21, 2026first mention
Oct 23, 2026latest mention
Why people recommend it
“the inference from together.ai feels like it might be better”
“Together.ai, Baseten, and others have already achieved higher throughput”
Show 1 more
“I’ve mostly settled on using a mixture of open weights models through Together.ai and Fireworks.ai”
switched from Claudeon “Anthropic's best AI model struggles to attract users…”
Caveats and dissent
No one in these comments warned against it.
Often compared with
Threads where it came up
- Ask HN: Some Sensible Alternative to Openrouter? 2 mentions
- Kimi K3.1 scores 55 on Artificial Analysis, placed on the Pareto line 1 mention
- DeepInfer: High-performance inference framework for DeepSeek models 1 mention
- Pop!_OS bans AI-generated code from much of its codebase 1 mention
- Anthropic's best AI model struggles to attract users as cheaper tools thrive 1 mention
- Gemini 3.5: frontier intelligence with action 1 mention
Also written as together.ai, Together.ai. Data: together-ai.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 12
“the inference from together.ai feels like it might be better”
“Together.ai, Baseten, and others have already achieved higher throughput”
“I use something like together.ai with an open weight model like glm 5.3”
“I’ve mostly settled on using a mixture of open weights models through Together.ai and Fireworks.ai”
“using them as a downstream provider through openrouter at some point (IIRC).”
“I've been reading about together.ai.”
“Open-source model inference providers (who do not have to bear the cost of training) seem able to do it at much lower prices.”
“Together.ai is a good US provider but then it's 15X more expensive”
“the inference prices somewhere like Fireworks or TogetherAI charges is comparable to what Google/AWS/Azure charge for the same model”
“we get better performance than big players (588 tok/s vs. Together AI's 298”
“Together AI is cheap but slower”
“falls back to DeepSeek/Together”