Claude AI Cost Calculator
Estimate standard text API costs for Claude Opus 5.5, Sonnet 5.5, and Haiku 5.5 from your own input and output token averages.
Select your model
Set your usage
Average tokens sent to the model in one request
Include reasoning or thinking tokens if your provider bills them as output. This estimate does not infer them.
All requests across your app for one day, not requests per user
Review results
Estimate for Claude Sonnet 5.5 at public standard text rates checked October 17, 2026.
Cost at different volumes
Each row keeps the same token assumptions.
| Total requests per day | Requests / month | Monthly | Annual |
|---|---|---|---|
| 100 | 3.0K | $9.00 | $109.50 |
| 1.0K | 30.0K | $90.00 | $1,095.00 |
| 10.0K | 300.0K | $900.00 | $10,950.00 |
| 100.0K | 3.0M | $9,000.00 | $109.5K |
Monthly estimates use 30 days. Annual estimates use 365 days.
Estimate covers public standard text input and output rates only. If your provider bills reasoning or thinking tokens as output, include them in your output-token estimate; this calculator does not infer them. It excludes cached-token pricing, batch discounts, external tools and search, embeddings, vector stores, hosting and infrastructure, negotiated discounts, free-tier credits, and image, audio, video, or voice usage.
Save your results
Get your cost estimate sent to your inbox. We'll also send tips on how to reduce your AI spending.
No spam. Unsubscribe any time.
Anthropic Claude Pricing
Public direct API text rates in USD per 1 million tokens. Checked Oct 17, 2026.
The rates below reflect today’s effective price. Scheduled changes are shown in the model notes.
| Model | Input / 1M | Output / 1M | Context window | Lifecycle and pricing notes |
|---|---|---|---|---|
| $4.00 | $20.00 | 1M |
| |
| $2.00 | $10.00 | 1M |
| |
| $0.10 | $0.50 | Not verified |
|
Claude Opus 5.5
- Standard text rates shown.
Claude Sonnet 5.5
- Standard text rates shown.
Claude Haiku 5.5
- Above 100,000 input tokens, $0.50 input and $2.50 output apply to the full request.
Prices cover standard text input and output only. The estimate excludes cached-token pricing, batch rates, tool and search charges, embeddings, vector stores, hosting and infrastructure, negotiated discounts, free-tier credits, and multimodal usage.
A context value is shown only when verified for this review. Confirm current terms with the provider before budgeting.
How Claude API text pricing works
Anthropic charges separately for input and output tokens. The estimate applies the selected model’s standard direct API rates to the average input and response sizes you enter, then scales by the request volume.
Claude Opus 5.5 and Claude Sonnet 5.5 have a 1 million token context window at standard pricing in the reviewed documentation. Claude Haiku 5.5 has a separate full-request price tier when the input prompt exceeds 100,000 tokens.
Prices and lifecycle information were checked on October 17, 2026. The table links to Anthropic’s pricing and model-lifecycle documentation. Retired Claude 3 and 3.5 models are not offered as current calculator choices.
