Tokenless
Shares rank 10 of 12 LLM routers by recommenders
Automatically switches each LLM request to a cheaper or stronger model to cut spend. Critics doubt answer quality and say switching providers can lose cache benefits.
Automatically switches each LLM request to a cheaper or stronger model to cut spend. Critics doubt answer quality and say switching providers can lose cache benefits.
13 people gave an opinion
- recommend it
- 6
- criticize it
- 7
- approval share
- 46%
Recommended in 2 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: not recommended
- May 2026: not recommended
- June 2026: not recommended
- July 2026: recommended
- August 2026: recommended
- September 2026: not recommended
- October 2026: not recommended
- November 2026: not recommended (month in progress)
Why it doesn’t carry the badge
- 6 people recommend itNeeds 10 or more, not met.
- 0.8 recommenders for every criticNeeds 2 to 1 or better, not met.
- Recommended in 2 of 13 monthsNeeds 4 or more, not 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
Smart, innovative approach
“It's a smart approach, definitely interesting. It all hinges on quality of course which im not convinced.”
Comment from 29 Jul 2026 in “Launch HN: Tokenless (YC S26) – Automatic model switching to save money” “the approach seems really innovative”
Comment from 1 Aug 2026 in “Everyone is building LLM routers, we deprecated ours”
What people warn about
Each mark is one comment
Provider switches reset cache benefits
“this only switches models if the cache is cold, because otherwise the economics of switching don't work”
Comment from 29 Jul 2026 in “Launch HN: Tokenless (YC S26) – Automatic model switching to save money” “Every switch to a different provider resets your cache affinity”
Comment from 30 Jul 2026 in “Launch HN: Tokenless (YC S26) – Automatic model switching to save money”
Other LLM routers people recommend
The four most recommended other LLM routers, 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 |
|---|---|---|---|---|---|---|
| OpenRouter | 666 | 321 | 67% | 13 | 6 mo8 owners | Approved |
| OpenCode Zen | 36 | 16 | 69% | 12 | — | Approved |
| Cortecs | 9 | 2 | 82% | 6 | — | — |
| Amazon API Gateway | 9 | 9 | 50% | 5 | — | — |
| TokenlessThis page | 6 | 7 | 46% | 2 | — | — |
What people said
All 16 comments that mention it, newest first. Each links to the original comment.
“the approach seems really innovative”
“It is just another metoo copy of OpenRouter”
“Every switch to a different provider resets your cache affinity”
“Tokenless Pro is 6.67 for the same performance as Luna.”
“It will inspire more confidence if you say your classifier.”
“they’ll be in the perfect place to do it because they’ll have the telemetry”
“Performance is worse on the two coding benchmarks and cheaper”
“this is going to be really bad for cases where there are many potential solutions”
“Since we fan out in parallel, by definition the latency is only at worst the latency of the slowest model.”
“It automatically works with multi-turn routing.”
“the quality could be really good”
“this would increase the cost for such queries”
“we trained custom models to predict LLM performance”
“would be expensive on the input token side”
“It's a smart approach, definitely interesting. It all hinges on quality of course which im not convinced.”
“this only switches models if the cache is cold, because otherwise the economics of switching don't work”
Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.