Up to 50x lower inference costs

Build AI data pipelines your team can trust

Sutro is a fully-managed, model-independent platform for aligning AI functions with your team’s judgment and running them at any scale. No prompt engineering, complex eval setup, or fine-tuning required. Fully hosted or in your own VPC.

Run on any model, including decision models.

Book a demo

Listing reviewer `review_listing()`

1 Align with your team’s judgment

Forest-green canvas backpack with a front zip pocket on a neutral studio background

Label this example

Needs workReady

The product interior isn’t shown.

Example 1 of 3Expert agreement: 96.1% (+18.7 pts)

2 Always know the best models for your task

Selected model:

3 Call your endpoint

import sutro as so

image = so.Image.from_file(
    "backpack.png"
)
result = so.run_function(
    "review_listing",
    {"image": image},
)

{
  "category": "backpack",
  "brand_fit": "on_brand",
  "listing_quality": "needs_work",
  "issues": [
    "Interior not shown"
  ]
}

19,573 processed$29.36Last 30 days

Lead scorer `score_lead()`

1 Align with your team’s judgment

Northstar Health

northstarhealth.example / about-us “better care starts before the visit” HQ: Austin, TX | team: ~240? (LinkedIn says 201–500) Healthcare workflow software for multi-site clinics; intake forms, scheduling, reminders + EHR integrations. CRM notes / updated Tue: sells to ops teams, NOT a care provider. Series B per old deck. Hiring implementation + enterprise AE roles. From website footer: patient engagement / reduce no-shows / HIPAA-ready workflows. Outbound notes: 3 locations mentioned in case study; customer count unconfirmed. See duplicate account “Northstar Hlth” before routing. Tech: API docs, Salesforce integration, calendar sync. Buyer likely VP Operations. Contact history still needs deduping.

Label this example

Strong fitWeak fit

Healthcare software vendor, not a care provider.

Example 1 of 3Expert agreement: 94.2% (+43.6 pts)

2 Always know the best models for your task

Selected model:

3 Run on your full dataset

import sutro as so

job = so.batch_run_function(
    name="score_lead",
    data="prospect_database.csv",
)
results = so.await_job_completion(job)

{
  "company": "Northstar Health",
  "fit": "strong",
  "priority": "high",
  "reason": "Matches our target industry and company size."
}

prospect_database.csv · 13,789,571 records84% complete

11,589,167 processed$139.07

Candidate reviewer `review_candidate()`

1 Align with your team’s judgment

Morgan Lee

RESUME_final_v3 (2).pdf — copied text MORGAN LEE | Senior Software Engineer [email protected] / portfolio available EXPERIENCE 2023–present Northline / Sr SWE — data platform • Owned ingestion jobs + on-call; Python / SQL; migrated legacy pipelines, “~40% fewer failures” 2019 - 2023 Software Engineer Built APIs, distributed processing & internal analytics. Stack listed elsewhere: postgres, Kafka, Python3, SQL. EDUCATION: B.S. Computer Science SKILLS / Python, SQL, distributed systems [page 2] Projects: event ingestion service; warehouse migration. Formatting lost in export. Six years of professional engineering experience as of this resume.

Label this example

SeniorManager

Six years of engineering; no direct reports documented.

Example 1 of 3Expert agreement: 91.6% (+11.2 pts)

2 Always know the best models for your task

Selected model:

3 Run on your full dataset

import sutro as so

job = so.batch_run_function(
    name="review_candidate",
    data="candidate_resumes.csv",
)
results = so.await_job_completion(job)

{
  "years_experience": 6,
  "role_fit": "strong",
  "seniority": "senior",
  "summary": "Strong platform experience; leadership scope unclear."
}

candidate_resumes.csv · 400,000 records64% complete

256,429 processed$3.08

“Sutro gives us a framework to develop judges that we have faith in.”

Sr. Software Engineer

+60%Accuracy−94%Inference cost64 annotations per function

“Sutro saves our team countless hours, and it gives us the invaluable ability to measure, optimize, and prevent regressions against our domain expertise.”

CTOAI Data Marketplace+28%Accuracy−73%Inference cost163 annotations per function

“Sutro unlocks use cases that weren't previously possible from a cost perspective.”

Principal Data Platform Engineer

+18%Accuracy−98%Inference cost30 annotations per function

*Average per customer function.

Request customer case studies

Why you'll love it

Forget prompts, fine-tuning, and evals

Just upload a sample of your data, give feedback on a handful of examples, and watch quality climb automatically.

Evaluation quality

Never get locked into a model

Run your tasks on any AI model. Sutro helps you find the best fit for your quality and cost needs, and easily switch when new models come out.

Cost–quality frontier

Surprisingly affordable

Run millions of AI tasks for the price of a coffee run. Unlock use cases that seemed out of reach, while raising the quality bar.

Before

1042 · support✓

1043 · billing✓

0 records processed

After

1042 · support✓

1043 · billing✓

0 records processed

How it works

Define and Align

Sutro surfaces hard cases for your experts to annotate - then optimizes directly against their feedback.

app.sutro.sh/functions/lead-qualifier

Optimize

Collecting feedback · 1/3

Is this company a good fit for our sales team?

Example 1 of 3

Cedar Labs · website + CRM export

industry: Software Development | employees: 201–500
site: “Your embedded product team. We design & build for clients.”
crm_note: “SaaS? AE to confirm” | enrichment: B2B Software
pricing: project-based; no subscription product found

Is this a qualified lead?Reviewing example

Model Sweeps

Benchmark models on your task to build your own frontier of cost and quality. See which models deliver the best quality for your budget, then choose the tradeoff that works for you. Redraw your task frontier with a single click when new models are released.

Scale

Run your function where you see fit: on your own inference providers, or using Sutro's ultra cost-efficient batch inference service. Process millions of rows and billions of tokens at a time.

score_leads("prospect_database.csv")Auto-scaling

13,789,571 records

Optimize tasks, not models.

Models change fast. Keep your task, judgment, and evals intact while Sutro finds your best quality–cost options. Choose a model yourself, or let Sutro choose.

Lead qualificationToday

Bring your task, data, and judgment. Sutro handles the rest.

Finding GPUs💰💰
New model release!
Evals
× 6 checks failing
Prompt versions
External annotators💰
Model fine-tunes
Labeled datasets
Eval reports
85.7% ↓ 3.2 pts
Model APIs
401 Unauthorized
Model output spreadsheets
Retry queues
429 · 128 queued
Inference scaling
Monitoring
p95 4.8s

Built-in evals
Automated harness optimization
Throughput-optimized inference
Centralized task management
Continuous model comparison
API, SDK, and MCP access
Fully hosted or in your own VPC

Pricing that scales with you

All plans include a free two-week trial.

Book a demo

Starter

$50 / month

Includes $10/month in usage credits

Up to 2 deployed functions
5 saved functions
Additional usage billed separately

Scale

$500 / month

Includes $100/month in inference credits

Up to 25 deployed functions
Unlimited saved functions
Additional usage billed separately

Book a demo

Enterprise

Custom

Pre-paid inference discounts available

Self-hosted options available
Integrate with your own providers
Advanced support and deployed engineering plans

Talk to sales

Batch inference · Open-weight models

Machine-time pricing means you only pay for the compute your workload actually consumes. Data can be read from your own S3-compatible storage.

Estimated price $120

Number of records 10 million

Average uncached input size

Frequently asked

Is this an evals product?

Evaluation is part of Sutro, but it’s not the whole product. Sutro turns expert feedback into optimized, reusable AI Functions that can run on any model and at any scale.

How does Sutro’s inference work?

Sutro offers a managed, high-throughput batch inference service for running Functions on open-source models.

Using Sutro’s inference is optional. Functions can also run in real time on any provider you choose, or be exported for local or edge inference.

How does Sutro work with decision models like Jev and Clef?

Sutro helps you teach models your team’s standards, compare their quality and cost, and turn them into reusable AI Functions. Decision models like Jev and Clef can power those Functions when the task calls for structured choices rather than free-form text.

Can Sutro use image inputs and other modalities? Can it call tools?

Yes. Sutro supports images, PDFs, and web search capabilities today. Additional modalities and custom tool calling are available on a per-request basis.

What models does Sutro use?

Sutro is model-agnostic, and we support a mix of open-source and proprietary models. Small, open-source models commonly outperform larger proprietary models on expert-aligned data processing tasks. Sutro helps automatically find the best model for your needs.

Can I self-host Sutro? Do you support BYOC and BYOK?

Yes. Sutro can be managed as SaaS or entirely self-hosted. You can bring your own provider keys and cloud credentials in either case.

How does Sutro compare to prompt engineering, fine-tuning, or RL?

Sutro is designed to be more robust, accurate, and scalable than prompt engineering, and more data efficient, portable, and re-trainable than fine-tuning or RL. We encourage you to try it out and see for yourself!

What will you scale with Sutro?

Get Started

Build AI data pipelines your team can trust

Sutro is a fully-managed, model-independent platform for aligning AI functions with your team’s judgment and running them at any scale. No prompt engineering, complex eval setup, or fine-tuning required. Fully hosted or in your own VPC.

Listing reviewer review_listing()

Lead scorer score_lead()

Candidate reviewer review_candidate()

Why you'll love it

Forget prompts, fine-tuning, and evals

Never get locked into a model

Surprisingly affordable

How it works

Define and Align

Cedar Labs · website + CRM export

Model Sweeps

Scale

Optimize tasks, not models.

Bring your task, data, and judgment. Sutro handles the rest.

Pricing that scales with you

Starter

Scale

Enterprise

Batch inference · Open-weight models

Frequently asked

What will you scale with Sutro?

Listing reviewer `review_listing()`

Lead scorer `score_lead()`

Candidate reviewer `review_candidate()`