Published in Getting started
Pricing & Usage
Understanding how AI pricing works helps you build better apps and control costs. This guide explains our pricing philosophy and gives you tools to estimate and optimize your usage.
Why Usage-Based Pricing?
We get asked about pricing a lot, so let’s be upfront about why we charge the way we do.
We want to give every builder access to the best AI models available. Not watered-down versions, not artificially limited options - the actual best models from OpenAI, Anthropic, and Google.
The challenge is that these models have real costs. Running GPT-5.5 costs more than running GPT-5 Nano. Claude Opus 4.8 costs more than Claude Haiku 4.5. If we charged a flat rate, we’d have to either:
- Restrict access to premium models - forcing everyone onto cheaper models
- Charge everyone the premium price - making it unaffordable for many builders
- Lose money - which means we can’t stay in business and keep building tools for you
Usage-based pricing solves this. It means:
- Budget-conscious builders can use fast, cost-efficient models like Gemini 3.5 Flash or GPT-5 Nano and keep costs minimal
- Quality-focused builders can access the most powerful reasoning models like o3 or Claude Opus 4.8 when they need them
- Smart builders can mix and match: use affordable models for simple tasks, premium models for complex ones
This isn’t about being greedy. It’s about building a sustainable business that can keep providing best-in-class AI tools to every type of builder, at every budget level.
How Pricing Works
Your Plan Includes Usage
Builder, Studio, and Studio Pro include a monthly usage allowance:
| Plan | Monthly price | Included usage each month |
|---|---|---|
| Builder | $99/mo | $30 |
| Studio Pro | $299/mo | $100 |
If you stay within your allowance, you pay nothing extra. If you need more, you can purchase additional credits in advance.
Event credits from a QR code
If you sign up from an event QR code, your event credits (for example $25) come with your own personal organization. You are never added to the event host’s organization. To keep the credits from going to people who sign up in bulk, they wait until you verify a mobile phone number or add a card (you are not charged for the card).
Right after you sign up, a dialog asks you to do this. You cannot skip it: until your credits are in your balance, the Builder stays closed, so you never hit an “Insufficient credits” error on your first project. Enter your number, type the 6-digit code we text you, and the dialog confirms the credits are in your balance before it opens the Builder. If the credits cannot be added, the dialog says so and lets you try again. If you close the page, the dialog opens again the next time you sign in.
One phone number or card unlocks free credits for one account. If your signup is held for a quick account review, the dialog tells you and lets you continue once you are verified.
Build For You and Fractional CTO
Build For You ($2,500/mo) and Fractional CTO (starts at $12,500/mo) add a dedicated model capacity lane, and let you bring your own Google, OpenAI, and Anthropic keys with no platform fee on that usage. These plans do not include a usage allowance: usage bills at standard rates, or directly by the provider on your own keys. See Model Keys and Dedicated Capacity.
What Counts as Usage?
Usage is measured in tokens, the units AI models use to process text. Roughly:
- 1 token ≈ 4 characters or ¾ of a word
- A typical message might use 500-1000 tokens total (input + output)
Different models have different costs per token. Premium models cost more, efficient models cost less.
Want to understand exactly how tokens work? Check out our Understanding Tokens guide with an interactive tokenizer.
Estimate Your Costs
Use this calculator to estimate your monthly AI costs based on expected usage:
Model Pricing Comparison
Here’s how different models compare on price. Choose based on your needs:
Most Cost-Effective Models
These models offer excellent quality at the lowest prices:
Premium Models
When you need the best quality, these models deliver:
Prices per 1 million tokens, including the platform markup:
| Model | Provider | Input per 1M tokens | Output per 1M tokens |
|---|---|---|---|
| Gemini 3.5 Flash | $1.95 | $11.70 | |
| GPT-5 Nano | OpenAI | $0.065 | $0.52 |
| GPT-5.6 Luna | OpenAI | $0.26 | $1.56 |
| Claude Haiku 4.5 | Anthropic | $1.30 | $6.50 |
| GPT-5 Mini | OpenAI | $0.33 | $2.60 |
| GPT-5.5 | OpenAI | $6.50 | $39.00 |
| Claude Sonnet 4.6 | Anthropic | $3.90 | $19.50 |
| Claude Opus 4.8 | Anthropic | $6.50 | $32.50 |
| o3 | OpenAI | $2.60 | $10.40 |
| Gemini 3.1 Pro Preview | $2.60 | $15.60 |
Strategies to Optimize Costs
1. Match Model to Task
Don’t use a premium model for simple tasks. Consider:
| Task Type | Recommended Approach |
|---|---|
| Quick Q&A, FAQs | Gemini 3.5 Flash or GPT-5 Nano |
| General conversation | GPT-5 Mini or Claude Haiku 4.5 |
| Content creation | GPT-5.5 or Claude Sonnet 4.6 |
| Complex analysis | o3 or Claude Opus 4.8 |
| Processing long documents | Gemini 3.1 Pro Preview or GPT-4.1 (1M token context) |
2. Optimize Your Prompts
Shorter, clearer prompts use fewer tokens:
- Be specific about what you want
- Remove unnecessary context from system prompts
- Use concise instructions instead of verbose explanations
3. Consider Response Length
If your app doesn’t need long responses, instruct the model to be concise. Output tokens typically cost more than input tokens.
4. Use the Right Context Window
Models with larger context windows (like Gemini 3.1 Pro Preview with 1M tokens) are great for processing long documents. But if you’re just doing quick Q&A, you don’t need to pay for that capacity.
Real-World Examples
Example 1: Customer Support Bot
Use case: Answering common questions, routing complex issues
Recommended: Gemini 3.5 Flash
Estimated cost on Gemini 3.5 Flash: about $33.15 per month for 10,000 messages of 500 input and 200 output tokens each ($1.95 input and $11.70 output per 1M tokens).
Example 2: Content Writing Assistant
Use case: Helping users write blog posts, emails, marketing copy
Recommended: GPT-5.5
Estimated cost on GPT-5.5: about $188.50 per month for 5,000 messages of 1,000 input and 800 output tokens each ($6.50 input and $39.00 output per 1M tokens).
Example 3: Legal Document Analyzer
Use case: Reviewing contracts, extracting key terms, summarizing agreements
Recommended: Gemini 3.1 Pro Preview (1M token context)
Estimated cost on Gemini 3.1 Pro Preview: about $36.40 per month for 1,000 messages of 8,000 input and 1,000 output tokens each ($2.60 input and $15.60 output per 1M tokens).
Example 4: Research Assistant
Use case: Deep analysis, multi-step reasoning, complex problem-solving
Recommended: o3
Estimated cost on o3: about $46.80 per month for 2,000 messages of 3,000 input and 1,500 output tokens each ($2.60 input and $10.40 output per 1M tokens).
Your Billing page
Everything about money lives on one page: open the account menu and choose Billing (or go to Settings → Billing). Only organization owners and admins see it; other members see a short note that billing is managed by their owners and admins.
The page reads from top to bottom:
- Overview: your plan, your organization’s credit balance, what you spent this month, whether auto top-up is on, and a warning when something needs you (low balance, a failed payment, a cancelled plan). Below it are the main actions: Add credits, Manage plan, Payment method and Set up auto top-up.
- Plan and subscription and Add-ons.
- Organization credit balance: one wallet that pays for every app and build in your organization. Add credits here.
- Payment method and Auto top-up: refill the balance automatically when it drops below an amount you choose.
- Spending limits: caps on what the organization, an app or a member may spend. They limit spending from the one wallet; they are not separate money.
- Usage and spend: totals first, then the breakdown by model, app, workspace, source, member, consumer and service, for the time range you pick. Costs are in US dollars; usage is in tokens or service units. Every breakdown adds up to the same total. Usage that a breakdown cannot assign (for example an automation with no member) shows as its own row.
- Software factory spend and funding: what building and hosting projects cost.
- Billing notifications: who gets an email when credits run low or a spending limit is near.
- Invoices and receipts and Transactions and top-ups: your records.
Each section opens when you click it. Old links and bookmarks, such as the former Usage page, open the matching section.
We’ll automatically notify you when your credits are running low, so you have time to top up before your app pauses.
FAQ
What happens if I run out of credits?
Your app’s AI functionality will pause until you purchase more credits. We’ll send you notifications as your balance gets low so you’re never caught off guard. You can top up anytime from your billing settings.
How do I add more credits?
Open Billing from the account menu and choose Add credits, or open the Organization credit balance section. Purchase credits in advance. Credits are prepaid: there are no surprise bills or overages. You control exactly how much you spend.
Do unused credits roll over?
Yes. Your monthly allowance adds on top of any remaining balance instead of resetting it, and credits never expire.
Why do output tokens cost more than input tokens?
This reflects how AI providers price their APIs. Generating new text (output) requires more computation than processing existing text (input).
Can I change models mid-conversation?
Your app uses one model at a time, but you can change it anytime in the Build settings. The change applies to new conversations.
What Usage Covers
Usage billing covers more than chat interactions and tool calls. These features draw from the same credit balance:
Voice Interactions
Real-time voice conversations with AI are expensive to run. Because voice is part of usage billing, it is available to everyone, not just select customers. You pay for what you use, making voice accessible regardless of your plan.
Knowledge Source Embeddings
Embedding costs for knowledge sources are part of usage billing, so you can add large numbers of documents to power your app’s knowledge base and pay only for what you process.
Image & Video Generation
AI-generated images and videos are resource-intensive. Usage billing lets us offer these creative tools to everyone. Generate marketing visuals, product demos, or custom content - paying only for what you create.
Usage Details
The Usage and spend section of your Billing page breaks down your AI usage across apps and models, so you can see exactly what you’re paying for and track costs over time.
We’re building toward a future where every AI capability is available to every builder, with transparent, pay-for-what-you-use pricing.
Need Help Choosing?
If you’re not sure which model fits your use case, check out our Choosing a Model guide for detailed recommendations based on different scenarios.
Using with MCP
You can access billing and usage information programmatically using the Chipp MCP Server.
Available Tools
| Tool | Description |
|---|---|
get_credits | View current credit balance |
get_subscription | Get subscription tier and details |
get_usage | Get detailed usage breakdown |
Example Prompts
"How many credits do I have left?"
"What's my current subscription plan?"
"Show me my usage breakdown for this month"Workflow: Usage Monitoring
You: Show me my current billing status
AI: [Calls get_credits, get_subscription]
Subscription: Builder ($99/mo)
Credit Balance: $18.50 remaining
Monthly Allowance: $30 included
Usage this month:
- GPT-5.5: $8.20 (410K tokens)
- Claude Sonnet 4.6: $2.30 (115K tokens)
- Gemini 3.5 Flash: $1.00 (90K tokens)MCP server access requires a Builder plan or higher. See the MCP Setup Guide to get started.
Ready to build it?
Tell Chipp what you want. Start free, or book a session and build it with our team.