Macha
Features Macha on Zendesk Build with Sidekick Build with Claude Code & Codex Use Cases Integrations Pricing Documentation API Reference Building Effective Agents
Log in Start free trial

Simple credits. Clear outcomes.

Macha bills per agent run, not per action. One run handles the whole job — triage, lookup, reply, tag — for a single model rate. Pick a bundle and dial the model to control spend.

Monthly Annual Save 20%

Starter

$299 /mo

3,000 credits ($0.10/credit)

White-Glove Launch

$799 one-time

A Macha Forward-Deployed Engineer builds & tunes your agents on your real tickets and gets you live — then hands off.

  • Done-for-you build
  • Up to 4 agents, integrations & custom tools
  • 6 guided sessions over 4–6 weeks

Billed once on your first invoice, on top of your plan — not recurring. Need an FDE long-term? Talk to sales.

  • Sidekick — your in-dashboard AI copilot
  • 1 integration
  • 3 knowledge sources
  • 3 agents
  • Agent Auto-Eval (50 conversations / agent)
  • API access
  • Email support
See everything included
  • AI Agent + Tool Builder
  • Email & live-chat channels
  • Knowledge base sync
  • Credit usage dashboard
  • 7-day free trial, no credit card
Start free trial

7-day free trial, no credit card required

Recommended

Professional

$699 /mo

10,000 credits ($0.07/credit)

White-Glove Launch

$799 one-time

A Macha Forward-Deployed Engineer builds & tunes your agents on your real tickets and gets you live — then hands off.

  • Done-for-you build
  • Up to 4 agents, integrations & custom tools
  • 6 guided sessions over 4–6 weeks

Billed once on your first invoice, on top of your plan — not recurring. Need an FDE long-term? Talk to sales.

  • 10 integrations
  • 10 knowledge sources
  • 25 agents
  • 3 scheduled triggers
  • 5 custom API tools
  • Studies (AI Analysis)
  • AI Agent Evaluation
  • Agent Auto-Eval (50 conversations / agent)
  • AI Agent + Tool Builder
  • API access

Support

  • Email support
  • Slack support
  • Video support
See everything included
  • Sidekick AI copilot
  • Everything in Starter
  • Email & live-chat channels
  • Knowledge base sync
  • Credit usage dashboard
  • 7-day free trial, no credit card
Start free trial

7-day free trial, no credit card required

Enterprise

Custom

Unlimited credits

Volume pricing for high-throughput teams

  • Unlimited integrations, knowledge & agents
  • 20 scheduled triggers
  • 20 custom API tools
  • API access

Support

  • Email support
  • Slack support
  • Video support

Includes the full Professional feature set — every integration, builder and evaluation tool — with no usage caps.

Talk to sales
How credits work — each agent run consumes credits, set by its model

How credits actually work.

The one thing to understand: an agent run is what consumes credits, and the model it runs on sets how many. Everything else follows from that.

Credits are consumed by agent runs. A run is an agent handling one ticket or message from start to finish.
  • A single run can do many things — triage the ticket, look up an order, draft a reply, tag and route it, add an internal note.
  • That entire run is billed once. How many credits it consumes is set only by the model the agent runs on: GPT-5.4 (default) = 3, GPT-5 = 2, GPT-5.4 Mini = 1.
  • You are never charged per step, per tool call, or per action inside a run.
No — this is the most common misunderstanding, so let's be crystal clear: one run is one charge, full stop.
  • Whether the agent does one thing or ten — triage, look-up, draft, tag, summarize — it is still a single run.
  • A GPT-5.4 agent that triages a ticket, drafts a reply, and tags it consumes 3 credits total, not 3 + 3 + 3.
  • You're billed per run, by model — never per step.
The model the agent runs on — nothing else. You set it per agent:
  • GPT-5.4 Mini — 1 credit
  • GPT-5 — 2 credits
  • GPT-5.4 (default, best output) — 3 credits
Run complex, customer-facing agents on GPT-5.4 and simple ones (triage, tagging, FAQ look-ups) on a cheaper model to control spend.
Yes, and we want to be upfront about it: on live chat, each AI reply is its own run.
  • An email reply that resolves a ticket in one go is a single run.
  • A back-and-forth chat with five AI replies is five runs.
  • If most of your volume is live chat, run those agents on a cheaper model (GPT-5.4 Mini = 1 credit) to keep costs down.
No. Everything that happens inside a run — calling tools, searching your knowledge base, looking up an order, the model's own reasoning — is included in that run's single charge. You only ever pay the one model rate for the run.
It depends on your plan and on monthly vs annual billing:
  • Starter — about $0.10 / credit ($299 / mo for 3,000 credits).
  • Professional — about $0.07 / credit ($699 / mo for 10,000 credits).
  • Save 20% on every credit by paying annually.
  • Enterprise — custom volume pricing.
Your agents pause until credits reset on your next billing date — nothing is lost, and your agents, integrations and knowledge sources stay configured. To keep going immediately you can:
  • Top up — 1,000 for $99, 5,000 for $449, or 10,000 for $799 (top-up credits never expire and are used after your monthly allowance).
  • Or upgrade to a larger plan.
No — there are no overages, ever. Macha never bills you for more than your plan, and nothing keeps charging in the background. If you use up your monthly credits, your agents simply pause until they reset — you're never auto-charged extra. To resume before the reset you can top up (credits never expire) or upgrade — both are choices you make, so your bill never moves without you. No surprise invoices, no runaway spend.
GPT-5.4 is the default at 3 credits per run — the best model, for the best output. You set it per agent:
  • Keep customer-facing agents on GPT-5.4.
  • Drop simpler ones (triage, tagging, internal summaries) to GPT-5 (2 credits) or GPT-5.4 Mini (1 credit).
Rule of thumb: the more complex the job, the better the model you should pick.
A one-time $799 done-for-you setup: a Macha Forward-Deployed Engineer builds and tunes your agents on your real tickets and gets you live, then hands off.
  • Done-for-you build of up to 4 agents, integrations and custom tools.
  • 6 guided sessions over 4–6 weeks.
  • Billed once on your first invoice, on top of your plan — not recurring.
Need an FDE embedded longer-term? Talk to sales.
Yes. Building and managing agents, connectors, tools and sources over the API costs zero credits — there's no metering, on every plan including trials. The API configures your agents; it doesn't run them. You only spend credits when an agent actually runs and does work.
Neither directly — you pay per agent run. A single email reply that resolves a ticket is one run; a live chat is one run per AI reply. Billing tracks the work your agents actually do, not how many tickets or customers you have.
Yes. No lock-in — cancel anytime and keep access through the end of your billing period. Starter and Professional both start with a 7-day free trial, no credit card required, so you can build agents and watch Macha work before you pay.

Which plan fits?

Tell us your ticket volume and the model your agents run on — we'll do the credit math. One ticket = one run.

1,000

Model your agents run on

1,000 tickets × 3 credits / run

3,000 credits / month

Recommended plan

Starter

Each ticket is one agent run — no matter how many steps the agent takes inside it. Live chat bills per reply, so multi-message chats use more. Top up or size up anytime.

Credits per run, by model
GPT-5.4 Mini 1 credit / run
GPT-5 2 credits / run
GPT-5.4Default 3 credits / run
Claude Sonnet 4 / 4.5 9 credits / run
Llama 3.3 70B 1 credit / run
Llama 3.1 8B 0.5 credits / run
Mixtral 8×7B 0.5 credits / run

Built For Trust.
Designed For Privacy.

Your data is safe with Macha AI. We meet the highest security standards so you can focus on support without compromise.

GDPR Compliant

Fully aligned with global data protection and security standards.

Zero Data Retention Policy

We never store customer information or your customer conversations.

Zendesk
5.0 on Zendesk Marketplace

Loved by support teams worldwide

See what support teams are saying about Macha AI.

The application seems excellent to me! We are still testing, and we need support for some details and they were extremely efficient too!

Daniela Costa

Daniela Costa

Head of Support, Seabra

Macha has been a great addition to our support toolkit. It generates clear, well-organized responses that fit naturally into our workflow. One feature we particularly appreciate is its ability to automatically reply in the same language as the ticket.

Marius F

Marius F

Support Head, Zentana

We've been using Macha for a little while now and it's been really great addition so far! It's powerful, convenient, and makes getting work done a lot easier for our agents.

Alexander Wedén

Alexander Wedén

Head of Support

Support team is very helpful and responsive. Really enjoy how lightweight this is within Zendesk itself vs other more intrusive tools.

Cathleen Wright

Cathleen Wright

Zendesk Admin, Cortex IO

So far it's pretty good! Our queries are a little nuanced, so we can't always use it, but it's got enough utility for us. It can even incorporate our bilingual country with greetings in a second language.

Jae Oliver

Jae Oliver

Head of Support, Wise

Really enjoying using Macha, it has made a noticeable difference to our support team in a short amount of time. I really like the ticket summary feature, saves us a lot of time.

Harry Jackson

Harry Jackson

Head of Support, Crumb

Macha AI is a great addition to my workspace! It's powerful, convenient, and it really makes productivity so much easier for our agents!

Dave G

Dave G

Head of Support, Cyber Power Systems

Very impressed! AI integration for Zendesk has certainly come a long way and Macha seems to set the standard for now. This will for sure save lot of time in our support team.

Pauli Juel

Pauli Juel

Head of CS, Dokument24

Macha has been working great for us so far! The auto-responses are accurate and our resolution time has dropped significantly.

Lana T

Lana T

Zendesk Admin, Swotzy

Macha AI is a great addition. The knowledge base feature means our agents always have the right answers at their fingertips.

Mischa Wolf

Mischa Wolf

Head of Support, Topi

We're enjoying this integration so far. It's made our support team more efficient and our customers get faster responses.

Paula G

Paula G

Head of Customer Support, Xly Studio

The team enjoys using it. It saves considerable time on common questions and the integration options are excellent.

Kilian Leister

Kilian Leister

Support Head, Didriksons

Ready to cut your
support costs?

Start your free trial today. No credit card required — set up in minutes.

Get a demo Start free trial

7-day free trial · no credit card required