MindsHub pricing

Host any open agent.
Bring your LLMs or use ours.

Run agents like OpenClaw, NanoClaw, Anton, and Hermes on MindsHub. Pick the setup that fits — connect your own model accounts, or use the MindsHub model router for unified access to frontier and open models.

7-day free trial
Two simple tiers
Same model menu in both

Plans

One price. Two ways to run.

Hosting is $9.95/month either way. The difference is how you connect models — with your own LLM accounts, or through the MindsHub router.

Bring your own LLMs

Hosted · Bring your own LLMs

$9.95 / month

7-day free trial — billing starts after. Cancel anytime.

Host your AI agent on MindsHub and connect your own Anthropic, OpenAI, Google, or open-model accounts. You pay each LLM provider directly for token usage.

Hosted runtime for any supported open-source agent
Connect Anthropic, OpenAI, Google, and open-model providers
Same model menu as the router tier
Persistent memory, scratchpads, and workflows
Pay LLM providers directly with your own accounts
No token markup — provider rates pass through

Start with my LLMs →

Good when you already have provider accounts or volume discounts. Billing info required at signup to activate deployments.

Early access · Promo

MindsHub model router

Hosted + MindsHub Router

$9.95 / month Intro price

7-day free trial — billing starts after.
Includes 5M tokens · No LLM provider keys needed

Skip the model setup. Host your agent and route every call through one MindsHub endpoint that covers frontier and open-source models.

Everything in Bring your own LLMs
5 million tokens included each month
Unified router — Anthropic, OpenAI, Google, open models
latest:* aliases keep models up to date automatically
One bill instead of many provider accounts
Be among the first to shape multi-model billing on MindsHub

Claim the intro offer →

Best for getting started fast or testing many models without provider setup. Billing info required at signup to activate deployments.

Model router

One endpoint. Every model worth using.

The MindsHub router gives your agent a single connection to frontier and open-source models. Reference models by latest:* aliases so your agent stays current as providers ship new versions.

Unified access

One API surface for Anthropic, OpenAI, Google, and popular open models — no per-provider keys to manage.

Latest aliases

Point at latest:sonnet, latest:gpt, latest:gemini, and the router resolves to the current version.

Mix and match

Use strong reasoning models for planning and cheaper models for routine steps — all from the same endpoint.

Available models

Frontier and open-source, ready to call.

These models are available through the MindsHub router today. The same menu is accessible in the Bring your own LLMs tier when you bring matching provider accounts.

Anthropic Frontier

Alias	Resolves to
`latest:sonnet`	`claude-sonnet-4-6`
`latest:opus`	`claude-opus-4-7`
`latest:haiku`	`claude-haiku-4-5-20251001`

OpenAI Frontier

Alias	Resolves to
`latest:gpt`	`gpt-5.5` Default `reasoning.effort=low`
`latest:gpt-low` `latest:gpt-medium` `latest:gpt-high`	`gpt-5.5` With matching reasoning effort level
`latest:gpt-codex`	`gpt-5.3-codex`
`latest:gpt-mini`	`gpt-5.4-mini`
`latest:gpt-nano`	`gpt-5.4-nano`

Google Frontier

Alias	Resolves to
`latest:gemini`	`gemini-3.1-pro-preview`
`latest:gemini-flash`	`gemini-3-flash-preview`

Open source Open weights

Alias	Resolves to
`latest:kimi`	`kimi-k2p6`
`latest:deepseek`	`deepseek-v4-pro`
`latest:qwen`	`qwen3p6-plus`

FAQ

Common questions.

What is MindsHub?

MindsHub is a hosted platform for running open-source AI agents in the cloud. You get persistent state, memory, scratchpads, and workflows out of the box — and you choose how models are connected.

What's the difference between the two tiers?

Both tiers are $9.95/month for hosting. With Bring your own LLMs you connect your own provider accounts (Anthropic, OpenAI, Google, open models) and pay each provider directly for tokens. With the Router tier, MindsHub handles model access — you get one unified endpoint, 5M tokens included, and no provider accounts to set up. The $9.95 on the Router tier is a limited introductory price while we finalize usage-based token billing.

What does the $9.95/month include?

The hosted agent runtime — persistent memory, scratchpads, workflow execution, and platform updates. The Router tier additionally includes 5 million tokens of model usage each month through the MindsHub router.

What happens if I use more than 5M tokens?

You have two options. You can switch to Bring your own LLMs for overflow usage at any time, or contact us for a limit increase — we're happy to work with teams that need more headroom during the intro period. Standard usage-based pricing for the router will roll out soon — we'll publish a transparent rate card before it ships.

Which open-source agents can I host?

We're starting with four open-source agents on MindsHub: OpenClaw, NanoClaw, Anton, and Hermes — with more on the way. If you have a specific agent in mind, reach out and we'll let you know the timeline.

How do the latest:* aliases work?

Instead of pinning to a specific model version, reference an alias like latest:sonnet or latest:gpt. The router resolves to the current pinned version of that model family, so your agent automatically picks up new releases without code changes.

Can I switch between the two tiers later?

Yes. You can change between Bring your own LLMs and the Router tier any time from your MindsHub account settings. The same agent and project state carries over.

Is there a free trial?

Yes. Every plan starts with a 7-day free trial — billing begins after the trial period. You enter billing information at signup so deployments can activate and you can manage your agents from day one, but no charge is made until the trial ends. The Router tier additionally has a limited introductory price while we finalize usage-based token billing.