STRAITLY IS LIVE · 5% OFF FRONTIER · 10% OFF OPEN-WEIGHT · GET STARTED
Straitly compass logostraitly

A unified interface
for LLMs

ONE API · 177 MODELS
5% OFF FRONTIER · 10% OFF OPEN-WEIGHT

PAY AS YOU GO · NO COMMITMENT

Retro terminal showing the Straitly API
# straitly · chat completions
from openai import OpenAI

client = OpenAI(base_url=
  "https://api.straitly.ai/v1")

res = client.chat.completions
  .create(
    model=
      "anthropic/fable-5",
    messages=[{"role": "user",
      "content": "hello"}])

TRUSTED BY ENGINEERS USING

ReplitPerplexityopencodeClineRailwayWarpWarpReplitPerplexityopencodeClineRailwayWarpWarp

UNDER THE HOOD

Optimized routing for

Point your app at one endpoint, name the model, and Straitly handles the rest.

20.71 billion tokens served

TOKENS SERVED, AND COUNTING

Your appStraitly router
165+ models, 29+ providers
YOUR APPSTRAITLY
openai
5.6-sol

OPENAI

anthropic
fable-5.1

ANTHROPIC

gemini
3.6-flash

GOOGLE

YOUR DATA, NOT OURS

Prompts pass through.
They don't stay.

Pixel-art padlock with a ZDR display, sealed shut

Zero data retention

Requests and responses are never stored. Once your tokens are delivered, they're gone.

Never trained on

Your prompts never become training data. Not ours, not the providers' we route to.

SOC 2 Type II

Audited controls behind every request. The paperwork your security team asks for, done.

AICPA SOC 2 badge

ENFORCED ON EVERY REQUEST · EVERY PROVIDER

5% off frontier.
10% off open-weight.

UNDER LIST ON EVERY REQUEST, NO CAP

Indie hackers

Solo devs shipping real products.

Small startups

Pre-seed through Series A, before the bill gets scary.

Engineering teams

Teams spending real money on inference every month.

177 MODELS · 20 PROVIDERS

Same model.
Four prices.

Anthropic

4 MODELS· 4 CHANNELS

  • claude-fable-5.1: list $10.00 in / $50.00 out, Straitly $9.50 in / $47.50 out per million tokens
  • claude-opus-5: list $5.00 in / $25.00 out, Straitly $4.75 in / $23.75 out per million tokens
  • claude-sonnet-5: list $2.00 in / $10.00 out, Straitly $1.90 in / $9.50 out per million tokens
  • claude-haiku-4-5: list $1.00 in / $5.00 out, Straitly $0.95 in / $4.75 out per million tokens

OpenAI

3 MODELS· 4 CHANNELS

  • gpt-5.6-sol: list $4.00 in / $20.00 out, Straitly $3.80 in / $19.00 out per million tokens
  • gpt-5.6-terra: list $2.00 in / $12.00 out, Straitly $1.90 in / $11.40 out per million tokens
  • gpt-5.6-luna: list $0.20 in / $1.20 out, Straitly $0.19 in / $1.14 out per million tokens

Google

3 MODELS· 4 CHANNELS

  • gemini-3.6-flash: list $0.75 in / $3.75 out, Straitly $0.71 in / $3.56 out per million tokens
  • gemini-3.1-pro: list $2.00 in / $12.00 out, Straitly $1.90 in / $11.40 out per million tokens
  • gemini-3.5-flash-lite: list $0.30 in / $2.50 out, Straitly $0.28 in / $2.38 out per million tokens

Open-weight

5 MODELS· 4 CHANNELS

  • z-ai/glm-5.3: list $1.40 in / $4.40 out, Straitly $1.26 in / $3.96 out per million tokens
  • deepseek/deepseek-v4-pro: list $1.30 in / $2.60 out, Straitly $1.17 in / $2.34 out per million tokens
  • moonshotai/kimi-k3: list $2.85 in / $14.25 out, Straitly $2.56 in / $12.83 out per million tokens
  • qwen/qwen3.8-max: list $1.65 in / $4.95 out, Straitly $1.48 in / $4.46 out per million tokens
  • minimax/minimax-m3: list $0.28 in / $1.10 out, Straitly $0.25 in / $0.99 out per million tokens

Channel 1 is the lab's list price. OpenRouter adds an 8.5% fee on credits, Vercel adds 4% payment processing. Straitly is 5% under list on frontier models and 10% under on open-weight, on every account.

View all 177 models

FROM SIGNUP TO FIRST REQUEST

Signup to first request in five minutes.

01

SIGN UP

Email or Google. No form, no review, no sales call.

02

ADD CREDITS

Prepaid and pay as you go. Top up what you want to spend.

03

CREATE YOUR KEY

Live the moment you make it. Cap its spend if you like.

04

SWAP THE BASE URL

Point your app at Straitly. Nothing else in your code changes.

[ 5% OFF FRONTIER ][ 10% OFF OPEN-WEIGHT ]

LOADING...

FINAL STAGE

Stop paying Router tax.

Sign up, add credits, create a key. Five minutes to your first request, 5 to 10% under list.

PRESS START

PAY AS YOU GO · NO COMMITMENT · NO SALES CALL

BEFORE YOU ASK

Fair questions.

One API for every AI model. Instead of signing up with OpenAI, Anthropic, Kimi, Z.AI and everyone else separately, each with its own key and its own bill, you get a single key that reaches all of them. Requests route to the best provider for the job and fail over automatically when one goes down. Every account pays 5% under list on frontier models and 10% under on open-weight ones.

  1. STEP 01

    Sign up

    Email or Google. Your account exists the moment you finish. No application, no review.

    TIME TO ACCOUNT1 minute

  2. STEP 02

    Add credits and create a key

    Prepaid, pay as you go. Add funds when you are ready to run traffic and mint a key in the console. No sales call.

    BILLINGPer token, prepaid

  3. STEP 03

    Swap your base URL

    Point your existing OpenAI client at Straitly, then call any model in the catalog by name. Nothing else in your code changes.

    BASE URL"https://api.straitly.ai/v1"

  4. STEP 04

    Ship and scale

    Track spend per key as you grow, then stay usage-based or commit volume for a lower rate.

    EVERY REQUEST5-10% under list

We hold committed capacity with the frontier labs and major open source providers, priced below list. Most companies spend their growth budget on ads. We spend ours on your inference bill. Every account gets the margin, and word of mouth does the rest.

Indie hackers shipping real products, startups from pre-seed through Series A, and engineering teams with a real monthly inference bill. There is no application. Sign up and you are on the rate.

Not right now. Demand outran what a two-person team could fund, so we paused free credit. You pay only for what you use, at 5% under list for frontier models and 10% under for open-weight ones. No minimum, no subscription.

Yes. It's one line of change: swap the base URL, put in your API key, and your requests come to us. OpenAI-compatible API, every model in the catalog.

Yes. Bring your own provider keys and route them through us, or use ours and get one bill instead of four. Either way it's the same OpenAI-compatible API.

Minutes. Sign up, add credits, create a key, swap your base URL. Nothing waits on us.

Usage-based rates might change with market pricing. Committed rates never change. Lock a commit and that's your price, period.

We currently serve companies in the $2K to $100K a month range. For larger quota requirements we recommend going directly to the foundational providers - at that size you can probably secure an enterprise deal yourself.

Fallbacks are built in - requests reroute across providers before you see an error. We guarantee a 99% SLA and top-of-the-line time to first token.

Add a small amount, send real traffic, and compare. If we're not better, walk away. No commitment, nothing to cancel.