22 Assistants that advise.
6 Agents that act.
Crawling and uploads are unlimited at every tier — that's our infrastructure. You only pay for the generation tokens that hit the model. Agent tool calls (scrapes, WHOIS, audits) are unlimited too.
New to the distinction? See the 6 Agents → · See the 22 Assistants →
- ✓ 50,000 credits / month (1 credit = 1 token)
- ✓ All 22 ○ Assistants — full chat access
- ✓ Read-only ⚡ Agents: deep-research + SEO auditor
- ✓ 200M proxies + 4,000 tools
- ✓ 1 workspace · 3 projects
- ✓ Markdown / PDF / DOCX export
- ✓ 1,000,000 credits / month (1 credit = 1 token)
- ✓ All 22 ○ Assistants — full chat access
- ✓ All 6 ⚡ Agents including action-takers
- ✓ Outbound SDR runs every 30 min
- ✓ Inbox Triage runs every 15 min
- ✓ Approval-gate drafts in your outbox
- ✓ Multi-channel adapters (email, Slack, WhatsApp — coming)
- ✓ Unlimited workspaces + projects
- ✓ Memory across sessions
- ✓ Priority support
- ✓ 10,000,000 credits / month (1 credit = 1 token)
- ✓ Everything in Pro
- ✓ Up to 10 seats
- ✓ Shared workspaces + libraries
- ✓ Per-agent approval policies
- ✓ Audit log + SSO
- ✓ Self-serve billing dashboard
- ✓ Custom Agent slots (on request)
- ✓ API key access (beta)
Common questions.
What's the difference between an Assistant and an Agent? +
Assistants are 22 chat-driven specialists (HR, Sales, SEO, Legal, Finance and more). They have their own system prompts and tool catalogues, but they only respond to chat — they never take real-world action on their own. Agents are 6 (and growing) production workers that run on schedules (every 30 min, every 6 h, etc.), call real tools (ollagraph scrapes, WHOIS, AEO audits), and write to a workspace. Every action that could leave the platform — sending an email, publishing a post — is queued for your approval. You pick which Agents are read-only (advisory) vs which can write drafts. See /agents for the full list.
What's actually different about OllaSuper vs generic chat tools? +
Two things. First, 22 Assistants with their own system prompts, files + site grounded into every chat, memory across sessions, and real tool use backed by 200M owned proxies and 4,000+ scraping actors via ollagraph. Second, 6 production Agents that run on schedules and take real actions with approval gates — outbound SDR, SEO audits, content drafting, inbox triage, pipeline coaching, deep research. Generic chat tools rent their web access and don't have the scheduled-action layer at all.
Why are some Agents read-only on Free? +
Read-only Agents (SEO Auditor, Deep Research, Pipeline Curator) only produce reports — there's no risk surface. Action-taking Agents (Outbound SDR, Content Publisher, Inbox Triage) write to a workspace that's connected to real channels with your credentials. We gate those behind paid plans so we can offer per-workspace audit logging, approval policies, and the support layer customers actually need for action automation.
What counts as a credit? +
1 credit = 1 LLM token. Every token in the model's output counts against your monthly credit budget, including Agent reports and chat variants you reject. We track per-generation in the History panel so you can audit. Agent tool calls (scrapes, WHOIS) are unlimited — same as Assistant tools.
Do scans or uploads count against my credits? +
No. Crawling and file uploads are our infrastructure and are unlimited at every tier. You're only paying for the credits that hit the LLM.
Which models power the Assistants and Agents? +
All inference is routed through OpenRouter — never Anthropic. Assistants use a mix of OpenAI GPT-4o-mini / GPT-4o / Google Gemini / Mistral Large based on task. Agents pin specific models: outbound-sdr / inbox-triage / pipeline-curator on GPT-4o-mini, content-publisher on GPT-4o, and seo-auditor + deep-research on Tongyi DeepResearch 30B A3B (purpose-built for multi-step tool chains). You don't pick. You don't tune.
Do you train on my content? +
No. We send your prompts and selected source markdown to the LLM for inference only. We don't fine-tune on customer data and our vendors' APIs don't train on it either.
Can I cancel anytime? +
Yes. Cancel from your billing dashboard. Your plan stays active until the end of the billing period. Billing is handled by Dodo Payments.
Is OllaSuper DPDP-compliant? +
Yes. Designed-in. Workspace isolation, per-tenant encryption, delete-means-gone, and a published DPA on the legal page.