Help center
Frequently asked questions
Everything about Token Harbor — what it is, the models, API access, billing, rewards, and privacy. Can't find it? Ask us.
Help center
Everything about Token Harbor — what it is, the models, API access, billing, rewards, and privacy. Can't find it? Ask us.
Token Harbor is a unified AI gateway that gives developers and teams access to frontier AI models through a single API and dashboard.
Rather than maintaining the largest possible model catalog, Token Harbor focuses on curated frontier models from leading AI providers, helping users access the latest and highest-performing models without managing multiple accounts, API keys, billing systems, or provider integrations.
Token Harbor provides:
Users can either select a specific model directly or use TH Orchestra, which automatically classifies each turn and routes it to one of four specialized model pools — plan, build, compact, and chat.
We also prioritize trusted infrastructure and reliable providers. Whenever possible, Token Harbor works with established AI and cloud platforms to deliver stable, secure, and high-availability access to frontier models.
Token Harbor is designed for:
Managing multiple AI providers separately becomes complicated as your usage grows.
Token Harbor simplifies:
You can access models from multiple providers without managing separate accounts, API keys, payment methods, or integrations.
For users who prefer intelligent orchestration, TH Orchestra can automatically coordinate work across four specialized model pools — plan, build, compact, and chat.
We focus heavily on:
Transparency — users should understand which model handled a request, which provider served it, how costs are calculated, and how billing is tracked. We believe AI infrastructure should be observable, predictable, and transparent.
Direct Model Access — when you select a model, your request is sent directly to that model. No hidden model switching, no surprise substitutions. What you choose is what you use.
TH Orchestra — for users who prefer intelligent orchestration, it automatically classifies each turn and routes it to one of four specialized model pools: plan, build, compact, and chat. Users can choose between direct model access and orchestration depending on their workflow.
Frontier Models — we focus on a curated set of frontier AI models rather than maintaining the largest possible catalog. Our goal is to provide access to the latest and highest-performing models from leading AI providers.
Trusted Infrastructure — Token Harbor prioritizes reliability and long-term stability. We work with established AI and cloud providers whenever possible and maintain provider redundancy for many popular models. If one provider experiences issues, requests can automatically fail over to another provider serving the same model.
Built for Agents and Developers — Token Harbor is designed to work seamlessly with Claude Code, OpenHands, AutoGen, CrewAI, LangChain, and custom AI agents, as well as traditional AI applications and developer workflows.
Token Harbor focuses on frontier AI models from leading providers. Our catalog is intentionally curated to include the latest and highest-performing models rather than every model available on the market.
Current providers include:
New frontier models are added regularly as they become available. The latest supported models, pricing, context limits, and capabilities are always available on the Models page.
Some models may also be offered for free as part of promotional programs. Free model availability and usage limits are shown on the Models page.
TH Orchestra is Token Harbor's orchestration model. Instead of sending every request to a single fixed model, Orchestra analyzes the task and routes it through specialized model pools.
Examples include:
This allows complex workflows to use the most suitable model for each stage without requiring users to manually switch models.
When you select a model directly, every request is sent to that specific model — Claude → Claude, Gemini → Gemini, GPT → GPT.
When you select TH Orchestra, Token Harbor automatically classifies the task and chooses the most appropriate model pool for that stage of work.
Orchestra is designed primarily for coding agents, automation workflows, and multi-step tasks.
Token Harbor continuously monitors provider health and availability through internal health checks. If one provider becomes unavailable, Token Harbor can automatically route requests to another available provider serving the same model.
This helps improve:
In most cases, users continue using the same model without needing to take any action. For TH Orchestra, provider selection and failover are handled automatically as part of the orchestration process.
Yes. Token Harbor may provide free access to selected frontier models as part of promotional programs and community initiatives.
Models on permanent free routes carry an explicit :free model ID and are listed under Free on the Models page. That set changes as models are added or retired, so the Models page is the current list rather than this answer. Limited-time campaigns may add separate :free routes with their own allowance and end date.
Free model availability may change over time as new models are added and promotional programs evolve. Usage limits and eligibility requirements depend on account status and are described in the Billing & Usage section.
Yes. Token Harbor uses an OpenAI-compatible API format, making migration simple for most applications.
Example:
from openai import OpenAI
client = OpenAI(
base_url="https://tokenharbor.ai/v1",
api_key="YOUR_API_KEY"
)Yes. Streaming is supported using OpenAI-compatible APIs.
Yes. Token Harbor is designed for AI agent workflows and multi-model orchestration.
Compatible tools may include:
Yes. Users can create multiple API keys for separate projects, environments, AI agents, team usage, and different spending policies.
Each key may eventually support independent quotas and provider restrictions.
Planned / partial support may include:
Availability depends on upstream provider support.
Token Harbor supports pay-per-token wallet billing and optional Pass subscriptions.
You do not need a subscription. Every model listed on the /models page includes input pricing, output pricing, context limits, and provider information, priced in USD per 1M tokens — top up your wallet and usage is deducted automatically based on actual token consumption, with no monthly minimum and no commitment.
Passes are optional and bundle included usage for selected paid models. They suit regular use of the models a Pass covers; see the Subscriptions section below, or the Plans page for the current lineup and pricing.
TH Orchestra does not charge a separate orchestration fee. You are billed based on the actual model that processes your request, using the same per-token pricing shown on the Models page.
There is no volume discount and no orchestration surcharge — the per-token price shown on the Models page is the whole price, the same as it would be calling that model directly. The upstream model used and the final request cost are visible in the dashboard.
The dashboard is divided into two main sections.
Usage — a complete view of your account activity, including model usage, usage trends, request history and logs, request costs, and status and cache information. This lets you monitor both overall usage and individual request activity in one place.
Billing — your wallet and payment activity, including current balance, top-up history, spending history, cashback rewards, referral rewards, and promotional credits. You can also manage wallet top-ups and review your complete billing history.
Token Harbor uses a prepaid wallet system. When requests are processed:
Balances update automatically after each request.
Yes. Users can configure daily spend limits, monthly budgets, per-key quotas, and provider allow/block lists.
These controls are especially useful for teams, AI agents, automation systems, and shared environments.
Yes — unused wallet balance is refundable. To request a refund, email billing@tokenharbor.ai within 30 days of the original top-up.
Refund policy:
A Token Harbor Pass is an optional subscription that includes usage for selected paid models.
You do not need a Pass to use Token Harbor. You can continue to use available free models, or top up your wallet and pay per token. A Pass is useful if you regularly use the models included in Agent, Office, or Frontier and want a recurring included allowance.
Agent Pass at $2.99/month suits agents and scripts that call the API regularly. Office Pass at $19/month includes about six times that allowance and suits everyday writing, research, coding, and desktop-agent work. Frontier Pass at $99/month includes about thirty-two times the Agent allowance and suits heavy usage, frontier models, and professional workflows.
Those are the standard prices. A launch promotion is running, so the price charged today is lower — the Plans page always shows the current price. Higher tiers include the models available in the tiers below them.
Agent Pass adds GPT-5.6 Luna and MiMo V2.5 Pro.
Office Pass includes everything in Agent Pass and adds models such as Claude Sonnet 5, DeepSeek V4 Pro, Gemini 3.7 Flash, GLM 5.2, GPT-5.6 Terra, Grok 4.5, and Qwen3.8 Max.
Frontier Pass includes everything in Office Pass and adds models such as Claude Fable 5, Claude Opus 5, GLM-5.3, GPT-5.6 Sol, Grok 4.6, and Kimi K3.
Named models are the headline inclusions rather than the complete list: each Pass also covers every model priced at or below its own band, so coverage grows on its own as cheaper models are added. Where a model is served by more than one route, the Pass covers it on every route. Check the Plans page for the current list.
Pass allowance is usage value, not wallet credit. It is consumed automatically when you use models covered by your Pass, and is metered at each model's list price — so an allowance spent on an expensive model runs out sooner than the same allowance spent on a cheap one. The ceiling is in dollars, not in requests.
Each four-week allowance is divided into four 7-day windows, and each window contains one quarter of the four-week allowance. Pass allowance cannot be withdrawn or transferred to your wallet balance.
Based on a typical request of about 10K input and 1K output tokens. On Agent Pass, that is about: DeepSeek V4 Flash 800+; Qwen3.8-27B 800+; MiMo V2.5 Pro 900+; GPT-5.6 Luna 1,500+; MiMo V2.5 2,700+ — each a month, and each a floor rather than a cap.
Office Pass covers roughly 6× those figures, and Frontier Pass covers roughly 32× those figures, across a wider set of models. The Plans page shows which models each Pass reaches.
Your own mileage moves with prompt length: short prompts go further, long documents and long conversations go less far. An agent that makes several tool round-trips counts each round-trip as a request, so an agent loop consumes an allowance faster than the same amount of typing would.
No. Unused allowance in a 7-day window does not carry into the next window.
Your next allowance becomes available when the next 7-day window begins. You can view the current period and usage progress in your dashboard.
Pass allowance covers eligible usage included with your subscription. Wallet balance is credit funded through top-ups or promotions and is used for pay-as-you-go model calls.
Eligible calls consume the available Pass allowance. If that allowance runs out and pay-as-you-go continuation is enabled, further usage is deducted from your wallet balance at the rate applicable to your Pass.
Subscription payments do not add funds to your wallet, and Pass allowance cannot be withdrawn as cash or wallet credit.
No. Free allowance and Pass allowance are separate.
Subscribing does not reset, increase, or restore the current free allowance. If you have already used the current free allowance, it will become available again at the start of your next free-access period. You can use eligible paid routes covered by your Pass in the meantime.
Your free-model access remains available alongside the Pass and continues to use the free-model rules and retention settings selected in your dashboard.
Go to Dashboard → Billing and use the setting Keep working after my pass allowance runs out to control what happens next.
When this setting is enabled, eligible calls continue and additional usage is deducted from your Token Harbor wallet balance at the pay-as-you-go rate applicable to your Pass. Your available balance and hard spending cap still apply.
When the setting is disabled, the Pass acts as a hard limit. Covered calls stop when the allowance runs out and can resume when the next allowance window begins.
Monthly subscriptions are charged each month. Yearly subscriptions are charged once per year and offer a lower effective monthly price.
The yearly price shown on the Plans page includes both the annual total and its monthly equivalent. Choosing yearly billing changes the payment schedule, but included usage continues to refresh on the same four-week schedule.
Go to Dashboard → Billing and select Open billing portal.
The Stripe billing portal lets you view your current subscription and its renewal or cancellation date, update or add a payment method, view payment history and invoices, and cancel your subscription.
If you cancel, the billing portal shows the date on which the subscription will end. Your Pass remains active until the end of the paid billing period shown there.
Token Harbor offers free model access on selected models, a first top-up match for new accounts, spend milestones, and limited-time promotional programs. There is currently no sign-up credit and no cash referral reward. Available rewards and promotions may change over time.
Token Harbor provides free access to selected models through explicit :free model IDs. Your first free request starts a personal rolling 7-day period. The allowance is value-based rather than a fixed request count, because different models and requests have different costs. Your dashboard shows usage as a percentage.
Free routes never charge your balance. Their paid base-model counterparts remain available under the normal paid, zero-data-retention policy. Available models and limits may change over time.
There is no sign-up or welcome credit. Creating an account is free and no credit card is required, but the account starts with a $0 balance.
You can still start without paying: the free tier gives you access to selected models through their :free model IDs, described in the question above. When you are ready for the paid catalog, top up your wallet — the first top-up is matched (see below).
New users can receive a 100% bonus on their first wallet top-up. For example: top up $10 → receive $10 bonus; top up $50 → receive $50 bonus; top up $100 → receive $100 bonus.
The offer is available for 14 days after account registration. Maximum bonus is $100 per account.
Every account has a permanent invite code and invite link on the dashboard's Invites page. Share it and your friends can sign up through it — your dashboard shows how many people have joined on your invite.
There is no cash referral reward at the moment. Inviting a friend does not add credit to your balance. Referrals that were already pending before the reward ended still settle at the amount they were created under, and any creator or partner links that carry their own reward continue to pay under their own terms.
Invites remain subject to activity verification and anti-fraud checks. Sign-ups that share an address or device with the inviter, and batches of accounts created on disposable mailboxes, are not counted.
All promotional and incentive credits combined are capped at $500 lifetime per account. This includes top-up match bonuses, spend milestone credits, and future promotional incentives.
Once the lifetime cap is reached, wallet balances can only increase through direct top-ups.
Some rewards, promotional credits, and limited-time offers may include expiration periods depending on the campaign. Examples may include top-up match bonuses, seasonal promotions, and cashback campaigns.
Specific expiration details are shown in the dashboard or promotion details when applicable.
For paid models, Token Harbor does not retain your prompts or responses. We believe users should have access to frontier AI models without sacrificing privacy.
Paid models — prompts and responses are not retained by Token Harbor, there is no training on customer data, and they are designed for privacy-sensitive workloads.
Permanent free routes — Token Harbor may retain prompts and responses sent through explicit free routes after you opt in. Free routes are disabled by default, and adding a permanent free model requires consent covering the expanded scope, so earlier consent is never widened retroactively. Turning free models off stops future collection under the program and disables free routes, while data already collected during consent may be retained. Upstream providers separately process free-route content under their own terms, and their retention and training practices differ by provider. A limited-time campaign can instead expressly follow the paid-route zero-data-retention policy. Paid routes remain zero-data-retention. The models currently on free routes are listed on the Models page; see Privacy for the full policy.
No. Provider keys are stored securely on the backend and are never exposed publicly.
We believe transparency is critical for AI infrastructure. Token Harbor provides visibility into request logs, model usage, token consumption, request costs, and usage analytics.
For TH Orchestra requests, users can also see which model ultimately handled the request and how usage was billed. Our goal is to help users understand what they are using, how much it costs, and how requests are processed.
Token Harbor works with trusted model and infrastructure providers and continuously monitors service health. For many models, multiple upstream providers are available behind the scenes. If one provider experiences issues, requests can automatically fail over to another provider serving the same model.
This helps improve uptime, reliability, and request success rates while maintaining a consistent model experience for users.
We currently provide support through our Discord community (discord.gg/uBTckEReb5), email support (support@tokenharbor.ai), and documentation.
For technical issues, billing questions, API integration help, feature requests, or general feedback, users are encouraged to join our Discord community or contact the Token Harbor team directly.
We welcome feedback from users and developers. Bug reports, feature requests, and product feedback can be submitted through our Discord community (discord.gg/uBTckEReb5) or email support (support@tokenharbor.ai).
Our Discord community is typically the fastest way to reach the team and discuss new ideas with other users.
Still have questions?
Join the Discord or email us — we usually reply fast.