Baseten
Ranked 6 of 14 inference providers by recommenders
Hosted inference service for open-weight models, praised for fast throughput, low prices and responsive support. Critics point to weak security practices and poor handling of a security incident report.
Hosted inference service for open-weight models, praised for fast throughput, low prices and responsive support. Critics point to weak security practices and poor handling of a security incident report.
24 people gave an opinion
- recommend it
- 15
- criticize it
- 9
- approval share
- 63%
Recommended in 5 of 13 months
- November 2025: not recommended
- December 2025: not recommended
- January 2026: not recommended
- February 2026: not recommended
- March 2026: not recommended
- April 2026: recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: recommended
- October 2026: recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 15 people recommend itNeeds 10 or more, met.
- 1.6 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 5 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
Fast inference throughput and latency
“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” “There are other providers with much faster inference, like BaseTen at >100t/s”
Comment from 28 Aug 2026 in “GLM-5.3 is now open-weight” “Currently Baseten has ~610ms TTFT and ~82 tk/s for Kimi K2.6”
Comment from 23 Apr 2026 in “Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model” Responsive team and quick fixes
“Good in terms of prompt communication and fix. Absurdly bad in terms of reward.”
Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub” “kudos to the Baseten team for their super professional response”
Comment from 16 Sep 2026 in “We got admin access to Baseten's production GitHub” “kudos to their team for the fast patch”
Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub” - Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub”
Low price and transparent costs
“You can use "API-style" pricing on these providers which is more transparent to costs.”
Comment from 25 Apr 2026 in “Google to invest up to $40B in Anthropic in cash and compute” “open weight on a provider like BaseTen (solid performance, low price point)”
Comment from 7 Apr 2026 in “GPT 5.4 in practice – Stinks?” Reputable, provides real value
“Reputable hosting providers, e.g. Fireworks, Cloudflare, Baseten, whatever absolutely _do_ have a reputation to lose.”
Comment from 28 Oct 2026 in “Artificial Analysis Intelligence Index v5” “They've grown revenues at a solid clip, provide real value”
Comment from 23 Jul 2026 in “OpenAI and Anthropic unite against open-weight AI risks to their bottom line”
What people warn about
Each mark is one comment
Weak security practices
“An easily preventable issue with proper engineering culture around defense in depth and principle of least privilege”
Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub” “points to certain experience and expertise level for security practices”
Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub” Poor handling of security report
“I expect at least a preview of the report rather than being dumped on the signup page.”
Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub” “they don't care about bug reports.”
Comment from 15 Sep 2026 in “We got admin access to Baseten's production GitHub”
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 AI | 20 | 7 | 74% | 9 | — | Approved |
| fal.ai | 19 | 7 | 73% | 8 | — | Approved |
| BasetenThis page | 15 | 9 | 63% | 5 | — | — |
What people said
All 25 comments that mention it, newest first. Each links to the original comment.
“Reputable hosting providers, e.g. Fireworks, Cloudflare, Baseten, whatever absolutely _do_ have a reputation to lose.”
“I'm having a better time on BaseTen, but I only just started dabbling around there”
“serves deepseek faster than this already at a lower price”
“Baseten and Fireworks already do that for you.”
“Together.ai, Baseten, and others have already achieved higher throughput, lower latency, and lower E2E latency”
“kudos to the Baseten team for their super professional response”
“they don't care about bug reports.”
“An easily preventable issue with proper engineering culture around defense in depth and principle of least privilege”
“I expect at least a preview of the report rather than being dumped on the signup page.”
“Baseten carries the Soc 2 Type II and HIPAA Compliant logos on its front page.”
“Good in terms of prompt communication and fix. Absurdly bad in terms of reward.”
“That is great marketing for strix, pretty bad for baseten.”
“points to certain experience and expertise level for security practices”
“Baseten handled this well.”
“kudos to their team for the fast patch”
“I've gotten a few people set up with Baseten recently”
“it was a perpetual annoyance (from an engineering perspective)”
“I wrote this originally to replace Modal and Baseten, which I wasn't too pleased with”
“There are other providers with much faster inference, like BaseTen at >100t/s”
“Baseten.co's version got into a loop rather rapidly”
“have raised huge amounts of money and are part of the same US VC shitcycle”
“They've grown revenues at a solid clip, provide real value”
“You can use "API-style" pricing on these providers which is more transparent to costs.”
“Currently Baseten has ~610ms TTFT and ~82 tk/s for Kimi K2.6”
“open weight on a provider like BaseTen (solid performance, low price point)”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.