All your teams' AI spend. Under control.

AI adoption moves fast. Budgets and oversight need to keep up. MindsHub gives you one place to see usage, manage access, and set spending limits across providers from a single key. So teams can keep moving with confidence without losing control.

Help the developer reach MindsHub.

Press Space or tap to jump. Tap to jump.

Score 0

Misses 0 / 3

Space or tap to jump. Tap to jump.

The boss caught up.

Your score: 0

MindsHub

Spot and cut wasted spend across open and closed models.

Start your next idea on the always-free tier.

Try MindsHub

Inference console

Watch every model. Control every dollar.

Roles, model access and spend for everything your team calls through MindsHub Inference — open or closed models — in one console.

Skip the console tour

Console page console.mindshub.ai/settings/organization/roles

Organization / Billing

These records belong to your organization. Your role controls which billing details and actions you can access.

PlanPay as you go

Payment methodVisa ···· 4242

Remaining Balance $2,340.00

Usage Sep 1 – Oct 1, 2026

Credit spend this period

$4,040.00

Claude Sonnet 5.5 31% · $1,240.50
GPT-6 Astra 24% · $968.20
Claude Opus 5.5 17% · $706.00
Kimi K3 13% · $512.40
Gemini 3.8 Flash 10% · $398.75
GLM 5.3 5% · $214.15
MindsHub Air model 0% · $0.00

support-bot 28% · $1,140.00
Priya Nair 27% · $1,105.00
Sam Okafor 16% · $655.00
Omar Haddad 13% · $512.00
Lena Brooks 11% · $428.00
Dana Reyes 5% · $200.00

Engineering 49% · $1,960.00
Support 28% · $1,140.00
Data 13% · $512.00
Marketing 11% · $428.00

support-bot-prod 28% · $1,140.00
hub:anton:7c2048e1d3 17% · $705.00
sam-research 16% · $655.00
eval-pipeline 13% · $512.00
campaign-drafts 11% · $428.00
claude-code-dev 10% · $400.00
dana-notebook 5% · $200.00

7 budgets 1 at the limit 2 over 80%

Search budgets Applies to: Any Model: Any Status: Any

Budget	Spend	Used	Status
	of	0%	Normal
Acme LabsOrganization • All models	$4,040.00 of $8,000 / month	51%	Normal
EngineeringTeam • Claude Opus 5.5	$706.00 of $800 / month	88%	Over 80%
SupportTeam • All models	$1,140.00 of $1,500 / month	76%	Normal
DataTeam • Kimi K3	$512.40 of $500 / month	102%	Limit reached
Priya NairMember • Claude Sonnet 5.5	$382.10 of $400 / month	96%	Over 80%
support-bot-prodAPI key • All models	$41.20 of $75 / day	55%	Normal
DefaultWorkspace • All models	$3,612.00 of $6,000 / month	60%	Normal

Organization / Members

Organization roles

Organization roles apply across the organization. Workspace access also depends on workspace grants.

OwnerIncludes every Admin permission and protected ownership controls.

AdminManages members, invitations, teams, API keys, invoices, and billing (top-ups, card, auto-recharge), on top of everything a member can do.

MemberUses the product, sees who else is in the organization, and manages their own API keys.

User	Built-in role	Organization permissions
Dana Reyes (You)dana@acme.example	Owner	Built-in permissions
Priya Nairpriya@acme.example	Admin	Built-in permissions
Theo Granttheo@acme.example	Member	Member defaults
Sam Okaforsam@acme.example	Member	Member defaults
Lena Brookslena@acme.example	Member	Member defaults
Omar Haddadomar@acme.example	Member	Member defaults
Ana Silvaana@acme.example	Member	Viewer

Organization / Roles & permissions

These roles apply across the whole organization. Access inside a single workspace is decided on that workspace’s own Roles & permissions page. Compare the roles below, or create a custom role with the permissions your team needs.

Roles you can assign Owner and Admin hold the same permissions. What an Owner has that an Admin does not is ownership itself.

Owner Your role

Includes every Admin permission and protected ownership controls.

29 supported permissions

Cannot be given or taken away here

Admin

Manages members, invitations, teams, API keys, invoices, and billing (top-ups, card, auto-recharge), on top of everything a member can do.

29 supported permissions

Member

Uses the product, sees who else is in the organization, and manages their own API keys.

12 supported permissions

Viewer

A role we ship. Assigning it replaces the Member defaults.

10 supported permissions

Custom roles Roles somebody in this organization built. Assign one to a Member to replace their organization permissions.

Nobody here has built a role yet. The roles above are the ones we ship. Copy one to start from its permissions.

Showing 4 of 12 resource groups

Permission	Owner	Admin	Member
View members See who belongs to the organization. Read
Manage members Remove eligible organization members. Owners remain protected. Manage
Manage roles Create and assign custom roles, change built-in roles, and invite Admins. Manage roles

Permission	Owner	Admin	Member
View model rules See which models and providers are blocked for the organization, its workspaces and teams. Read
Manage model rules Block or allow a model or a provider for the organization, a workspace or a team. Manage

Permission	Owner	Admin	Member
Create API keys Mint a new API key for the caller’s own use. Create
Manage API keys Revoke any member’s API key. Only its owner can rename it. Manage
View API keys See the organization’s API key inventory. Read
Rename own API keys Rename keys belonging to you. Rename own keys
Revoke own API keys Revoke keys belonging to you. Revoke own keys

Permission	Owner	Admin	Member
View billing See the wallet balance, spend, and usage summary. Read
View invoices List and download the organization’s invoices. Read invoices
Top up wallet Add funds to the organization’s wallet and check a top-up’s status. Buy credits
Manage payment methods Add or replace the organization’s saved payment method. Manage payment methods
Manage auto-recharge Change automatic funding settings or resume paused automatic charges. Manage auto-recharge
Dismiss billing alerts Dismiss the organization’s low-balance warning. Dismiss alerts

Organization / Teams

Teams group organization members. Give a team an Admin or Member role in each workspace from Workspace access.

Name	Created on	Members	Workspace access	Role
All membersAll members · managed automatically	Aug 21, 2026	7 members	Workspace access	—
Engineering	Aug 24, 2026	4 members	Workspace access	Member
Marketing	Aug 24, 2026	1 member	Workspace access	Member
Support	Sep 2, 2026	1 member	Workspace access	Member
Data	Sep 9, 2026	1 member	Workspace access	Admin

Organization / Workspaces

Open a workspace to manage its settings and access. Organization roles and workspace roles are separate.

Name	Your workspace access	Created on
DefaultDefault · where unassigned resources live	Admin	Aug 21, 2026
Support bots	Admin	Sep 2, 2026

Organization / Model access

Each column shows that container’s own rules. Click a cell to block, allow, or clear one. A block anywhere wins, so a person in two containers is blocked if either blocks them. Until you add a rule, everyone can use everything.

Model	Everyone	Default	All members	Engineering	Marketing

Claude Sonnet
Claude Sonnet 5.5
Claude Sonnet 5
Claude Opus
Claude Opus 5.5
Claude Opus 5
Claude Fable
Claude Fable 5.1
Claude Fable 5
Claude Haiku
Claude Haiku 4.5

GPT
GPT-6 Astra
GPT 5.6 Sol
GPT Sol
GPT-6 Sol
GPT-6.1 Sol
GPT Terra
GPT 5.6 Terra
GPT Luna
GPT 5.6 Luna
GPT-6 Luna
GPT Codex
GPT 5.3 Codex
GPT Mini
GPT 5.4 Mini
GPT Nano
GPT 5.4 Nano
Text Embedding
Text Embedding 3 (small)

Gemini Pro
Gemini 3.1 Pro Preview
Gemini Flash
Gemini 3.8 Flash
Gemini 3.7 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash
Gemini 3 Flash Preview
Gemini Flash-Lite
Gemini 3.1 Flash-Lite

Grok
Grok 4.7
Grok 4.6
Grok 4.5

Muse Spark
Muse Spark 1.3
Muse Spark 1.2
Muse Spark 1.1

GPT-OSS 120B (Fireworks)
Kimi
Kimi K3
DeepSeek Flash
DeepSeek V4.1 Flash
Qwen
Qwen3.8-2.4T-A95B
GLM
GLM 5.3
GLM Flash
GLM 5.3 Flash

MindsHub Blaze

Jev
Jev 1.13.0

MindsHub Air Always available

allowed by a rule blocked by a rule inherited no rule (allowed) model rules under this provider

Organization / Audit log

Who changed what in this organization, with what credential, and when. Shows the last 90 days; use the date filters below to narrow the range.

Filter by actor email Filter by action All objects After Before

When	Actor	Action	Object
10/2/2026, 3:17:10 PM	priya@acme.example	update	entitlement_policy	Details
10/2/2026, 3:17:01 PM	priya@acme.example	insert	workspace_grant	Details
10/2/2026, 12:25:12 PM	dana@acme.example	update	organization_member	Details
10/1/2026, 6:02:44 PM	dana@acme.example	insert	team	Details
10/1/2026, 9:40:03 AM	theo@acme.example	revoke	api_key	Details
9/30/2026, 4:11:29 PM	sam@acme.example	insert	api_key	Details
9/30/2026, 11:58:17 AM	priya@acme.example	insert	entitlement_policy	Details
9/29/2026, 2:20:51 PM	dana@acme.example	update	organization	Details

API Keys

Create and manage API keys for external use.

New keys belong to Acme Labs

Service Accounts only

Name	Key Prefix	Principal	Created	Status
support-bot-prod	mdb_8fQ2kL1x	Service Account	Feb 3, 2026	Active Revoked
hub:anton:7c2048e1d3Agent key	mdb_UVEVZZbt	priya@acme.example	Sep 18, 2026	Active Revoked
sam-research	mdb_XGlUqr53	sam@acme.example	Aug 29, 2026	Active Revoked
eval-pipeline	mdb_tdMUI2U7	omar@acme.example	Jul 9, 2026	Active Revoked
campaign-drafts	mdb_KWkOMJds	lena@acme.example	Sep 12, 2026	Active Revoked
claude-code-dev	mdb_gRYVNbHL	priya@acme.example	Sep 1, 2026	Active Revoked
dana-notebook	mdb_Pw3sHq7v	dana@acme.example	Aug 22, 2026	Active Revoked
openclaw-test	mdb_IUJKFXzf	theo@acme.example	Aug 30, 2026	Active Revoked

Traces

7dLast 7 days

Every inference request your account has made, and the conversations they belong to.

5,036 requests·0.4% error rate·278ms / 2.5s p50 / p95·1.0s / 12s streamed

Time	Request	Model	Latency	Status	Trace
Oct 2, 1:13 PM	—	sonnet-5-5	801ms	OK 200	cfef7ca3
Oct 2, 1:13 PM	—	sonnet-5-5	17s	OK 200	339843cc
Oct 2, 1:13 PM	—	mindshub_air	642ms	OK 200	c792986c
Oct 2, 1:13 PM	—	gpt-6-astra	716ms	OK 200	6f7db9dd
Oct 2, 1:13 PM	—	qwen-3-8-a95b	1.1s	OK 200	710e3797
Oct 2, 1:12 PM	—	opus-5-5	1.4s	OK 200	a3ba4be6
Oct 2, 1:12 PM	—	opus-5-5	37s	OK 200	ee274284
Oct 2, 1:12 PM	—	gemini-flash	2.8s	Failed 503	0ecee1d5
Oct 2, 1:12 PM	—	kimi	883ms	OK 200	a5f89255
Oct 2, 1:11 PM	—	sonnet-5	1.3s	OK 200	7c161182

Credit spend this period

$4,040.00

Total tokens in 1,654,169,609 incl. 669M cached · 2.9M long context

Total tokens out 145,719,745

Total web searches 214

Model	Input	Cache write	Cache read	Output	Long context	Charge
Claude Sonnet 5.5	329M ($657.47)	34.7M ($86.84)	248M ($49.62)	44.7M ($446.57)	0	$1,240.50
GPT-6 Astra	48.4M ($484.10)	0	29.1M ($29.05)	7.9M ($396.96)	2.9M ($58.09)	$968.20
Claude Opus 5.5	91.8M ($367.12)	9.9M ($49.42)	141M ($28.24)	13.1M ($261.22)	0	$706.00
Kimi K3	93.9M ($281.82)	0	68.3M ($20.50)	14M ($210.08)	0	$512.40
Gemini 3.8 Flash	287M ($215.33)	0	150M ($11.96)	45.7M ($171.46)	0	$398.75
GLM 5.3	84.1M ($117.78)	0	33M ($8.57)	20M ($87.80)	0	$214.15
MindsHub Air model	3.4M	0	0	380K	0	$0.00
Total	938M ($2,123.62)	44.6M ($136.26)	669M ($147.94)	146M ($1,574.09)	2.9M ($58.09)	$4,040.00

Click to explore on your own · Use the controls for a guided tour

One platform

One model catalog. Three ways to use it.

Use MindsHub’s full model catalog through Inference, Cowork, or Code.

Your control plane

MindsHub Console

Manage access, track usage, and set budgets in one place.

MindsHub Inference

Use MindsHub models in your favorite agents, or build your own apps.

Explore Inference

MindsHub Agents

Two modes

Cowork

Give tasks to our agent workspace. Research, analyze, and create.

Explore Cowork

Code

Build features, fix bugs, and review code with our Codex-based coding agent.

Explore Code

Create free account

Pricing

Start free. Pay for what you use.

An always-free tier and pay-as-you-go access to every model at provider rates.

Free

Always free, for knowledge work with agents.

$0 / month

No credit card required.

Create free account

The MindsHub Air model for non-coding work
Use in our agents or yours
Classify, route and score with Jev
Daily limits under fair use Free covers everyday work with agents, in MindsHub Agents or your own. For bulk automation or high-volume workloads, use pay as you go. Read the fair-use policy

Pay as you go

Every model, billed at provider rates.

Per use at provider rates

Prepaid balance. No expiration or minimum spend.

Top up

Everything in Free, plus:

Every model in the catalog
Caching savings passed on to you
No plan limits; pay per use
Auto top-up with a monthly cap
Usage and spend tracking

See full pricing and model rates →

Read the text version

What is MindsHub?

MindsHub brings AI model access, usage, and spending into one place. Use models through MindsHub Inference in your own apps and agents, or work with them in MindsHub Agents. The MindsHub Console provides shared controls for access, billing, and budgets.

What problem does MindsHub solve?

An AI experiment can keep running long after someone stops thinking about it. As more people, agents, and applications call models, the bill grows. Without a clear view of usage, it is hard to tell which work is useful, what is wasting money, or who owns it.

Stopping the spend can create another problem: revoking an API key that several applications share can also take down a service people depend on. Teams need to understand what is running and set appropriate access and spending rules before a surprise bill forces a rushed decision.

How does MindsHub work?

For model requests made through MindsHub Inference, the console brings permissions, model access, usage, and budgets together. It helps teams answer four practical questions:

Who can do what? Create roles with the permissions people need, such as creating API keys or viewing billing, without giving everyone full administrator access.
Which models can they use? Manage access by provider or individual model, with rules for a team or the whole organization.
Where is the money going? Review daily spending by model, team, member, or API key, then inspect token usage and costs in the detailed breakdown.
When should we step in? Set a budget for a team, choose the models and budget period, and track spending against its limit. The Alert only option warns at the limit while keeping requests running.

Use this view to investigate waste, review who has access, and decide where to adjust spending.

How can you use MindsHub?

Use MindsHub’s full model catalog through Inference, Cowork, or Code.

MindsHub Inference

Use MindsHub models in your favorite agents, or build your own apps.

Connect a third-party agent or your own application to the API. Access models through OpenAI Chat Completions or Anthropic Messages with one MindsHub API key.

Explore Inference

MindsHub Agents: Cowork

Give tasks to our agent workspace. Research, analyze, and create.

Explore Cowork

MindsHub Agents: Code

Build features, fix bugs, and review code with our Codex-based coding agent.

Cowork and Code are two modes of MindsHub Agents.

Explore Code

How do you get started?

Create a free account, then choose whether to connect an app or agent through the API or use MindsHub Agents. Compare the plans below and visit pricing for the full terms and model rates.

Create free account

Free

Always free, for knowledge work with agents.

$0 / month. No credit card required.

The MindsHub Air model for non-coding work. Air uses a model selected for everyday knowledge work. The underlying model may change as better options become available.
Use in our agents or yours
Classify, route and score with Jev. Jev is TypeSafe’s decision model: it returns choices, scores and probabilities, not chat replies. Call it through the Decisions API as jev with your MindsHub API key.
Daily limits under fair use. Free covers everyday work with agents, in MindsHub Agents or your own. For bulk automation or high-volume workloads, use pay as you go. Read the fair-use policy

Create free account

Pay as you go

Every model, billed at provider rates.

Per use at provider rates. Prepaid balance. No expiration or minimum spend.

Everything in Free, plus:

Every model in the catalog
Caching savings passed on to you. When you resend content the provider already has cached, such as a long system prompt, it bills at the model’s lower cached-input rate, where the provider offers one.
No plan limits; pay per use
Auto top-up with a monthly cap
Usage and spend tracking

Top up

See full pricing and model rates

More information

Models Documentation Support Privacy Terms

Site index Full site text

Open this text as Markdown