Scale
1B+ memory-tokens held, reranking and priority on. Priced to your codebase.
Contact salesPay for capacity, seats, and overflow. Nothing else.
Estelle bills three meters: how much of your codebase it holds, who shares that memory, and anything past your cap. Recall is unlimited, queries are never metered, and your model's tokens stay yours: bring your own key or plan, we never mark up a token.
- unlimited recall, never metered
- unlimited queries
- bring your own key: your model tokens, never marked up
One repo, grounded and gated.
10M
memory-tokens held
about a 2M-token codebase, one repo
packageone size: 10M
1 seat, 1 repo
standard retrieval: dense and hybrid
$0no card needed
Your whole codebase, held.
100M
memory-tokens held
three package sizes, same Pro everywhere else
1 seat, every repo
standard retrieval: dense and hybrid
$29per month
The everything tier: the self-correcting suite.
250M
memory-tokens held
three package sizes, reranking always on
1 seat, every repo
retrieval with reranking, and priority
every Estelle suite: Gate, Memory, Code, Review, Monitor, Guardian, Orchestra, Security
$59per month
Team
One shared brain for the team.
any number of seats
every Estelle suite, for everyone: Gate, Memory, Code, Review, Monitor, Guardian, Orchestra, Security
shared memory with role-based access
stacks Memory Packs: +50M pooled each
Need a bigger pool? Memory Packs add +50M pooled for $15/mo each, and they stack.
The ladder is a real capability ladder: bigger packages hold more of your codebase, and retrieval sharpens with reranking on from Ultra up. Nothing below is artificially locked. You pay for held memory, seats, and overflow, and the answers get sharper because the memory gets bigger.
The foundation on every tier. The suite on Ultra.
Grounded memory and the gate ship on every paid plan. Then the ladder climbs in one clean step: at Ultra, best-in-class retrieval and the self-correcting suite (auto-repair and proactive auto-find, the surface that fixes your code for you) both turn on together. Ultra is the everything tier, and Team shares it across the whole team.
| Capability | Free | Pro | Ultraeverything | Team |
|---|---|---|---|---|
| Foundation | ||||
| Deterministic grounding gate on every proposed changeGate | ||||
| Whole-repo memory, cited to file and lineMemory | ||||
| Unlimited recall and queries, never meteredMemory | ||||
| Builds in your real files, on your own keysCode | ||||
| Runs under any MCP client: Cursor, Claude Code, Cline, Windsurf, Zed | ||||
| OpenAI-compatible API, one base URL and one model name | ||||
| Code graph: go-to-definition, references, blast radius, import cyclesMemory | ||||
| Always-on hooks: grounds every edit without the agent opting inGate | ||||
| The %estelle notebook magic for Jupyter, Colab, Kaggle and Deepnote | ||||
| Retrieval and review | ||||
| Hybrid retrieval with rerankingMemory | ||||
| Grounded review that lands on the pull requestReview | ||||
| Completeness gate: names the symbols a change failed to touchGate | ||||
| Session diary: what was decided, and where that decision livesMemory | ||||
| Context survival: checkpoint, resume and govern past the windowGuardian | ||||
| The self-correcting suites | ||||
| Traces a production failure to the file and lineMonitor | ||||
| Drafts the fix, proves it in a sandbox, opens a cited PRCode | ||||
| Holds answer quality across a long sessionGuardian | ||||
| Routes work across every provider key you ownOrchestra | ||||
| Continuous pentest against a sandbox cloneSecurity | ||||
| How it runs | ||||
| Propose-only by default: every fix arrives as a reviewable PRCode | ||||
| Opt-in auto-merge, off by default, only once the sandbox proves it greenCode | ||||
| Protected surfaces stay human-gated: auth, billing, schema, deploy | ||||
| Global kill switch and a signed audit line for every autonomous action | ||||
| Cost routing across your keys: cheap work never escalates itselfOrchestra | ||||
| In production, and across a team | ||||
| Grounds the agents already running in your production, not just your editorAgent | ||||
| Checks tool calls and claims against the repo as they happenAgent | ||||
| Slack, GitHub and Linear as connected surfaces | ||||
| Shared team memory with role-based access | ||||
| Pooled capacity that stacks with Memory Packs | ||||
Call the suite on Free or Pro and Estelle answers with a clean upgrade prompt, never a crash: reranking and the auto-repair and auto-find suite both stay an Ultra unlock. Auto-repair and proactive auto-find run today with a human on the autonomy dial, filing verified, tested fixes through your own tests. Fully autonomous self-healing in production is on the roadmap.
Three meters, and everything else is free.
The bill has exactly three lines. Everything that makes Estelle useful day to day costs nothing to use.
capacity
How many memory-tokens your plan holds at once: your code, docs, and sessions, swept into grounded memory.
seats
Who shares the memory. Solo tiers are one seat; Team is $79 per seat with role-based access.
overflow
Anything past your cap: $0.35 per 1M memory-tokens as you go, or a $15/mo Memory Pack that raises the cap by 50M. Packs stack, persist, and pool across a team.
free on every tierunlimited recallunlimited queriesBYOK model tokens
Pricing questions.
It measures what Estelle holds for you: code, docs, and sessions swept into grounded memory, embedded once on the way in. Your plan caps how many stay held at once; the 10M free tier holds roughly a 2M-token codebase. Recall does not consume them.