This free Claude cost calculator shows your likely monthly bill. Pay per token for Claude models. No monthly fee. Your real cost depends on your own usage, so enter your numbers above. We use the official Claude pricing page, last checked on November 3, 2026.
What is the Claude API?
The Claude API from Anthropic lets your own software use Claude models. Developers use it for support agents, research agents and especially coding agents, where Claude is widely used. Many no-code and voice tools, including GoHighLevel and Retell, also let you pick Claude as the model behind your agent.
Like other model APIs, you pay per token with no monthly fee. A token is a small piece of text, about three quarters of a word.
How much does Claude API cost?
| Model | Input / 1M | Cached input / 1M | Output / 1M | Cost per support chat* |
|---|---|---|---|---|
| Claude Haiku 5.5 | $0.10 | $0.010 | $0.50 | $0.0011 |
| Claude Sonnet 5.5 | $2.00 | $0.10 | $10.00 | $0.0215 |
| Claude Opus 5.5 | $4.00 | $0.20 | $20.00 | $0.0429 |
| Claude Fable 5.1 | $10.00 | $0.25 | $50.00 | $0.1061 |
Claude Haiku 5.5 is the low-cost model at $0.10 in and $0.50 out per million tokens (for prompts up to 100K tokens; longer prompts cost $0.50 and $2.50). Claude Sonnet 5.5 is the everyday agent model at $2.00 and $10.00. Claude Opus 5.5 costs twice Sonnet, and Claude Fable 5.1 is the top model at $10.00 and $50.00.
Ways to pay less, or more
- Prompt caching: reading cached text costs about a twentieth of normal input on most models (for example $0.10 instead of $2.00 on Sonnet 5.5). Writing to the cache costs more than normal input.
- Batch processing: 50% off for jobs that can wait.
- US-only inference: 1.1 times the normal price.
- Fast mode for Opus 5.5: up to 2.5 times faster at 2 times the price.
What is included, and what is not?
- Included: every model call, tool use (function calling), and the Messages API.
- Not included: Hosting for your agent code
- Not included: Web search ($10 per 1,000 searches)
- Not included: Cache write cost (cache reads are used here)
- Managed Agents runtime: $0.08 per session-hour, plus tokens.
- Code execution beyond 50 free hours a day: $0.05 per hour per container.
What does Claude API cost at 3 business sizes?
A support chat agent on Claude Sonnet 5.5, 22 working days, no buffer.
| Size | Chats per day | Plan | AI model | Platform | Total per month |
|---|---|---|---|---|---|
| Small | 20 | Pay as you go | $9.44 | $0.00 | $9.44 |
| Medium | 200 | Pay as you go | $94.38 | $0.00 | $94.38 |
| Large | 2,000 | Pay as you go | $944 | $0.00 | $944 |
One support chat costs $0.0011 on Haiku, $0.0215 on Sonnet and $0.0429 on Opus. Coding agents are much heavier: 10 coding jobs a day on Sonnet 5.5 cost about $110 a month, or $220 on Opus 5.5, because each job reads a lot of code at every step.
What hidden costs should you watch for?
- Cache writes. On Sonnet 5.5, writing to the 5-minute cache costs $2.50 per million tokens. Caching pays off only when text is reused.
- Long prompts on Haiku. Above 100K tokens, Haiku 5.5's price goes up five times.
- Web search. $10 per 1,000 searches, plus the tokens to read results.
- Thinking tokens. Extended thinking is billed as output.
How can you lower your Claude bill?
- Start with Haiku 5.5 for routing and simple replies.
- Keep your system prompt fixed so it stays cached.
- Use batch processing for reports and data jobs.
- Set spend limits in the Claude Console.
What are the main Claude API alternatives?
- OpenAI API cost calculator: GPT 6.1 Sol has the same list price as Sonnet 5.5.
- DeepSeek cost calculator: much lower token prices.
- Grok API cost calculator: one flagship model with a long context.
Who is Claude best for?
Good fit
- Coding agents and long, careful reasoning tasks
- Developers who want strong tool use
- Teams that already use Claude in other tools
Not the best fit
- Owners who do not want to write code
- Phone agents without a voice platform
What are the key Claude features?
- Four model levels: Haiku, Sonnet, Opus and Fable, from low cost to top quality.
- Tool use: Claude can call your functions and built-in tools like web search and code execution.
- Prompt caching: Big savings on repeated instructions and documents.
- Batch API: 50% off for work that can wait.
- Managed Agents: Run agents on Anthropic's infrastructure, billed per session-hour plus tokens.
- Long context: Up to 1M tokens on supported models.
How do you set up Claude?
The steps below show the general setup. Button names change often, so follow the idea of each step rather than exact labels.
- Create a Claude Console account. Sign up for API access and add billing.
- Set spend limits. Set a monthly limit and alerts first.
- Create an API key. Store it in your server's environment settings.
- Write the system prompt. Describe the job, rules and tools. Keep it stable so it gets cached.
- Define tools. List the functions Claude can call, with clear descriptions.
- Pick models. Start with Sonnet 5.5, test Haiku 5.5 for simple steps.
- Test and launch. Test on real examples, then launch and watch usage in the Console.
Tips from setup
- Use batch for nightly reports.
- Check cache hit rates in your usage data.
How do you calculate your Claude cost?
- What will Claude do for you?. Pick the job closest to yours. We fill in typical usage for that job, so you do not need to know anything about tokens.
- How many times a day?. Use a normal working day. A rough guess is fine, and we count 22 working days a month.
- Which Claude model?. Lower-cost models suit simple work. Move up only if the answers are not good enough.
- Read your answer. You see one monthly figure, the cost of each Claude task and what makes up the total.
Want to compare more tools at once? Use the main AI agent cost calculator.
How should you budget for Claude?
With a model API, you pay for what the model reads and writes, so your bill comes from your own design choices. The length of your instructions, how much chat history you resend, and how many steps each task takes matter as much as the price per token. Doubling the steps roughly doubles the cost.
To budget for Claude, run 20 to 50 real tasks through the model and record the tokens each one uses. Multiply the average by your expected monthly volume, then add 20% for retries and long requests. Set a monthly spending limit in your account so a bug cannot run up a large bill. Remember the API price does not cover hosting, your own development time or any paid tools your agent calls.
Claude pricing FAQ
How much does the Claude API cost?
Per million tokens: Haiku 5.5 is $0.10 in and $0.50 out, Sonnet 5.5 is $2 and $10, Opus 5.5 is $4 and $20, and Fable 5.1 is $10 and $50. There is no monthly fee.
Is there a discount for cached prompts on Claude?
Yes. Reading from the 5-minute cache is much cheaper than normal input, for example $0.10 per million tokens on Sonnet 5.5 instead of $2. Writing to the cache costs a bit more than normal input.
Does a Claude Pro or Max plan include API usage?
Max includes $100 a month in API credits and Ultra includes $200. Pro does not include API credits. Otherwise the API is billed separately.
Which Claude model is best for an AI agent?
Sonnet 5.5 is a common choice for agents. Haiku 5.5 is good for simple, high-volume tasks. Opus and Fable are for the hardest work where mistakes cost more than tokens.
How accurate is this Claude cost calculator?
It uses prices from the official Claude pricing page, last checked on November 3, 2026, and our own averages for typical usage. Treat your result as a planning estimate. Your real cost depends on your prompts, call lengths and busy days, so add about 20% and test with real work.
What does the Claude cost calculator leave out?
It does not count these costs: Hosting for your agent code; Web search ($10 per 1,000 searches); Cache write cost (cache reads are used here). It also leaves out tax and the time it takes to build and check your agent.
How do I work out what Claude will cost my business?
Answer the questions in the calculator at the top of this page with your normal daily numbers. A rough guess is fine. Then run a small test for a week and replace your guess with your real usage.
Get your Claude cost estimate
Now put in your own numbers. The Claude cost calculator at the top of this page gives you a figure in about a minute. Then run a small test with real work and compare your real usage with the estimate. Still deciding? Compare other AI tools.
Source and last checked date
All Claude prices on this page come from the official Anthropic Claude API pricing page, last checked on November 3, 2026. Cached input uses the 5-minute cache read price. US-only inference costs 1.1x. Haiku 5.5 prices shown are for prompts up to 100K tokens.
More cost calculators
Other ai model apis: OpenAI, DeepSeek, Gemini, Grok, Mistral.
All tools: n8n, Vapi, GoHighLevel, Retell AI, Bland AI, ElevenLabs, Synthflow, Make, Zapier Agents, Lindy, Botpress, Chatbase, Voiceflow, Relevance AI. Or go back to the AI agent cost calculator.