Tokenless (YC S26) 推出自动模型切换路由器，降低推理成本

The router that cuts your inference bill in half.

A drop-in replacement for your API calls — always routed to the right model.

Same quality, half the cost.

Most calls don’t need a frontier model. Tokenless fans out your request to a group of models and watches them think. Once a model is clearly on track, we select it and cancel the other models, and you only pay for what you need.

We expose an OpenAI and Anthropic compatible endpoint. Point your models at us and get started today!

refactor CLI options into an enum

this request

$0.0000

sent to Fable 5

$0.0000

−52%

· $0.0101 never billed

Measured, not marketed.

Solve rate and cost per task on public agentic benchmarks, against the best published run of each frontier model.

solve rate

40.2%

33.0%

32.8%

30.9%

26.8%

24.5%

Tokenless Pro

GPT-5.6 Sol

Claude Opus 5

Tokenless Ultra Saver

Claude Fable 5

Gemini 3.6 Flash

avg $/task

$0.57

$1.50

$1.64

$2.25

$2.58

$3.32

Gemini 3.6 Flash

Claude Opus 5

Tokenless Ultra Saver

Tokenless Pro

GPT-5.6 Sol

Claude Fable 5

See what you’d save.

YOUR MONTHLY LLM SPEND

YOUR MONTHLY BILL

$14K

/mo

OFF YOUR BILL

you pay $26K/mo

saved $14K/mo

you pay $26K/mo

saved $14K/mo

$40K/mo — your bill today

YOUR NEXT 12 MONTHS

TREND: RAMP AI INDEX · +11.0%/MO

NEW MONTHLY BILL

$26K/mo

BLENDED SAVINGS RATE

REQUESTS REROUTED

CURRENT BILL

$40K/mo

Estimates use published token prices (including cache rates) and editable routing assumptions in the source. Your rate depends on your traffic. Spend history & trend: Ramp AI Index — AI spend per employee, Jun 2025–Jun 2026, matched to the cohort your spend sits in and extrapolated at its trailing 12-month growth.

Built by AI researchers from Google DeepMind, Princeton, and UC Berkeley.
Backed by Y Combinator.

Cut the bill. Keep the quality.

Book a demo and we’ll run the numbers on your actual traffic — or swap two lines and see for yourself.

Book a demo