CodingDocumented overviewLast checked Oct 1, 2026

HarnessRouter: Pricing, Features & Best Use Cases

One API to run agent harnesses like Codex, Claude Code and Hermes as backends inside your own product.

Is HarnessRouter right for you?

HarnessRouter suits developers who want to put Codex, Claude Code or Hermes behind one API in their own product and pay only for active agent-work minutes plus model usage at catalog price. Based on the vendor's documentation, not on a hands-on test.

Best for: Developers building agent-powered products

Also a good fit for

  • Teams comparing Codex, Claude Code and other harnesses
  • Companies wanting self-hostable agent infrastructure

Consider another tool if free plan limited to 30 agent-work minutes and 2 concurrent tasks

Or if

  • Tracing only included on the $1,000 Scale plan while in beta
  • Agent memory billed separately per GB-hour

HarnessRouter pricing and usage limits

Prices checked Oct 1, 2026 on the official US pricing page. Official pricing ↗ Prices and limits change often.

Vendor pricing page re-checked automatically 12 days ago: no changes detected.

HarnessRouter pricing page with plans and prices — screenshot of the coding AI tool, Oct 1, 2026
The official HarnessRouter pricing page as we saw it. harnessrouter.ai, captured Oct 1, 2026

Free access and trial conditions

Free plan with no card and no expiry; running tasks draws from top-up credit

No separate trial

Paid plans: what changes as you upgrade

Free API

Free source (opens in a new tab)

Month, annual commitment

For: Exploring and configuring your first integration

Limits

  • 30 agent-work minutes
  • 2 concurrent tasks
1 more
  • Task records kept 7 days

Includes

  • Console and workspaces
  • Own keys, no markup
1 more
  • Top-up credit to run models without a provider key

API included

Developer API

$20/mo source (opens in a new tab)

Month, annual commitment

For: First integration

Limits

  • $20 of usage included
  • Unlimited concurrent tasks
1 more
  • 1 workspace

Includes

  • Agent work $0.014 per minute after included
  • 30% off top-up rates
1 more
  • Own keys or platform keys

API included

Production API

$200/mo source (opens in a new tab)

Month, annual commitment

For: Apps serving real users

Limits

  • $200 of usage included
  • 5 workspaces

Includes

  • Agent work $0.010 per minute
  • 50% off top-up rates
1 more
  • Tracing as $50 per month add-on

API included

Scale API

$1,000/mo source (opens in a new tab)

Month, annual commitment

For: High-volume production

Limits

  • $1,000 of usage included

Includes

  • Agent work $0.006 per minute
  • 70% off top-up rates
1 more
  • Tracing included (beta)

API included

Enterprise API

Custom pricing source (opens in a new tab)

Unknown, annual commitment

For: Custom terms

Includes

  • Custom usage and volume
  • Custom terms

API included

Usage caps, credits and extra costs

Top-up credit $10 minimum with 5.5% processing fee (minimum $0.80), agent work $0.020 per active minute off-plan, agent memory $0.0000840 per GB-hour on Free, tracing add-on $50 per month

Not stated

What is HarnessRouter, and how does it work?

HarnessRouter provides a unified API and console for running agent harnesses such as Codex, Claude Code, Hermes, DeepSeek Harness and Qwen Code as backends for your product. Each task runs in an isolated sandbox that HarnessRouter provisions and operates, with streaming, session continuation, file artifacts and recovery handled by the platform. The open-source Community Edition (Apache 2.0) implements the same Unified Harness Protocol for self-hosting. The Cloud offering bills model usage at catalog price with no markup, or lets you bring your own provider keys, and charges only for active agent work minutes; a Harness Arena compares time, cost and accuracy across harness and model combinations.

HarnessRouter homepage — screenshot of the coding AI tool, Oct 1, 2026
HarnessRouter's official site: how the product presents itself. harnessrouter.ai, captured Oct 1, 2026

What you provide and what you get back

How HarnessRouter works: what you provide, where it runs and what you get backYOU PROVIDEYour inputTask prompt sent through the APIChoice of harness and modelYour own provider keys or platfor…Files and tools for the sandboxCODINGHarnessRouterWeb, APIfrom $20/mo (Developer)free tier availableaccount requiredchecked Oct 1, 2026YOU GET BACKThe resultStreamed agent eventsFile artifactsPer-task receipt with cost breakd…Retained step-by-step recordinput → HarnessRouter → output · from the vendor's own pages, no hands-on test unless stated
What you give HarnessRouter and what comes back, from its documentation

You provide

  • Task prompt sent through the API
  • Choice of harness and model
  • Your own provider keys or platform keys
  • Files and tools for the sandbox

You get back

  • Streamed agent events
  • File artifacts
  • Per-task receipt with cost breakdown
  • Retained step-by-step record

Where you can use it

Platforms
Web, API
Account
Required

Where HarnessRouter is most useful

Scenarios are worked out by our editors from the documentation; the actual result depends on your input and plan.

Adding agent-backed features to a SaaS product without building harness infra

Who
SaaS developers
You provide
Task requests from your product's users
Expected result
Agent-backed feature running in an isolated sandbox
Plan needed
Developer
Limitation
You still integrate the API into your own product source (opens in a new tab)

Switching between coding-agent harnesses behind one API

Who
Platform engineers
You provide
The same task sent to different harnesses
Expected result
One API contract across Codex, Claude Code and others
Plan needed
Free
Limitation
Free plan covers only 30 work minutes source (opens in a new tab)

Benchmarking harness and model combinations on a real task

Who
AI teams
You provide
A real task and several harness-model pairs
Expected result
Cost, speed and accuracy comparison in Harness Arena
Plan needed
Free
Limitation
Model usage is billed on top at catalog price source (opens in a new tab)

What HarnessRouter does, and where it stops

HarnessRouter homepage — screenshot of the coding AI tool, Oct 1, 2026
Feature overview on the official site. harnessrouter.ai, captured Oct 1, 2026

Single API contract across multiple agent harnesses

Gives one API contract across Codex, Claude Code, Hermes, DeepSeek Harness and Qwen Code Avoids rewriting integrations when you change harness

Access: All plansLimit: Harness list may change over time source (opens in a new tab)

Isolated sandbox per task with streaming and artifacts

Runs each task in an isolated sandbox with streaming, artifacts and recovery Removes sandbox ops work

Access: All plansLimit: Waiting time is free but active work is billed source (opens in a new tab)

Bring-your-own-keys or platform keys at catalog price

Lets you bring provider keys or use platform keys at catalog price Keeps model billing transparent

Access: Platform keys need top-up creditLimit: Memory and tracing are extra source (opens in a new tab)

Harness Arena for cost/speed/accuracy comparison

Compares harness and model combinations in Harness Arena Helps choose by cost, speed and accuracy

Access: Listed in featuresLimit: Benchmark scope is not detailed source (opens in a new tab)

HarnessRouter: strengths and limits

Where HarnessRouter is strong

Limitations to check before paying

  • Free plan limited to 30 agent-work minutes and 2 concurrent tasks Hobby projects exhaust the free quota quickly documented source (opens in a new tab)
  • Tracing only included on the $1,000 Scale plan while in beta Debugging on lower tiers has less visibility documented source (opens in a new tab)
  • Agent memory billed separately per GB-hour Long-lived agents add a second metered line documented source (opens in a new tab)
  • Requires integration work in your own product You need engineering time to wire it in documented source (opens in a new tab)

How to use HarnessRouter for running an agent harness as a backend for your product

HarnessRouter documentation — screenshot of the coding AI tool, Oct 1, 2026
HarnessRouter documentation: where the steps below come from. harnessrouter.ai, captured Oct 1, 2026

Set up HarnessRouter

  1. Create a free HarnessRouter account and open the console
  2. Create a workspace and add your provider keys, or top up credit for platform keys
  3. Choose a harness such as Codex or Claude Code

Example: running an agent harness as a backend for your product

  1. Send a task request to the API with the chosen harness and model
  2. Stream events and read the produced file artifacts
  3. Continue the same session with a follow-up request
  4. Open the receipt to see agent-work, memory and model lines

Review and export the result

  1. Check that waiting time shows as $0.00 free wait time on the receipt
  2. Compare cost across harnesses in Harness Arena before settling
Example prompt suggested by our editors (not a recorded output of the product)
Review the attached repository for failing tests, fix the smallest bug you can find, and return the patch as a file artifact.

HarnessRouter integrations and API

HarnessRouter documentation — screenshot of the coding AI tool, Oct 1, 2026
HarnessRouter documentation (continued). harnessrouter.ai, captured Oct 1, 2026

Native integrations and export formats

Export: File artifacts

API access and separate billing

HarnessRouter has no public API in its official documentation. Unified Harness Protocol; open-source Community Edition under Apache 2.0 API documentation ↗

Privacy, data use and commercial rights

Summarized from the vendor's current policies; this is not legal advice and a vendor's badge is not an independent audit.

How your inputs and outputs are handled

Each task's step-by-step record is retained with its cost breakdown

unknown

7 days on the free plan; longer on paid plans per the pricing FAQ

Commercial use and plan restrictions

unknown

Retention is shorter on Free

Controls for business users

  • Self-hostable Community Edition
  • Own provider keys

Policies: harnessrouter.ai/legal/privacy

Best HarnessRouter alternatives for different needs

"Better suited" is based on documented features and pricing, not on a head-to-head test.

Cursor: better suited to

GitHub Copilot: better suited to

Replit: better suited to

Devin Desktop (formerly Windsurf): better suited to

Alternatives
AlternativeWhen to choose itPricingLimitation
Cursor——Compare
GitHub Copilot——Compare
Replit——Compare
Devin Desktop (formerly Windsurf)——Compare

Explore HarnessRouter further

Related to HarnessRouter

HarnessRouter user reviews

No user reviews yet.

Used HarnessRouter? Be the first to share your experience.

Write a review

Reviews are checked by a moderator before they appear. Your email is never published. Plain text only.

Your rating (required)

Show what you made or what went wrong. Images are published only if the review is approved; location data is removed.

    HarnessRouter FAQ

    How much does HarnessRouter cost?

    Plans are Free at $0, Developer at $20, Production at $200 and Scale at $1,000 per month, each including that amount in usage; Enterprise is custom. source (opens in a new tab)

    What is billed as agent work?

    Executing a step or tool such as running code or browsing, at $0.020 per active minute off-plan; waiting for models, you or queues is free. source (opens in a new tab)

    Is there a markup on models?

    No, models are billed at their listed catalog price, or you bring your own keys and your provider bills you. source (opens in a new tab)

    How long is task data kept?

    On the free plan the step-by-step record is kept for 7 days and then deleted. source (opens in a new tab)

    Can I self-host it?

    Yes, an open-source Community Edition under Apache 2.0 implements the same Unified Harness Protocol. source (opens in a new tab)

    Sources and review methodology

    Official sources and verification dates

    Not verified: Training use; Docs content (fetch); Retention on paid plans.

    How we documented and maintain this page

    Every fact about HarnessRouter above comes from the 3 official pages listed here, last compared on Oct 1, 2026; we have not run HarnessRouter ourselves, so it has no editorial score. How we check and re-check pages.

    Article updated Oct 10, 2026; prices checked Oct 1, 2026. Outbound links to vendors are plain links; we do not earn commissions. How we review · Report an error