This Claude API cost calculator estimates first-party Anthropic token charges for current Claude Fable, Opus, Sonnet and Haiku models, plus the retained Sonnet 4.5 legacy option. Enter the separate uncached-input, prompt-cache and output usage from a representative request, then multiply it by your request volume.
Claude pricing changes with processing mode, cache operation and, on supported models, inference geography. Web search also has a per-search fee. Confirm material budgets against Anthropic’s official Claude API pricing.
Estimate your Claude API cost
All listed token rates, processing modes and model status checked: 19 October 2026. All estimates are in USD.
Claude Sonnet 5 · Standard · Global · 1,000 requests
- Uncached input
- $2.00
- 5-minute cache writes
- $0.00
- 1-hour cache writes
- $0.00
- Cache reads
- $0.00
- Output
- $5.00
- Web search
- $0.00
- Token subtotal
- $7.00
- Average per request
- $0.007
Planning estimate only. Actual usage, retries, tool output, cache hits and contract terms can change the billed amount.
Current Claude API rates used by this calculator
All figures below are USD per million tokens for first-party Claude API use. Batch cache rates are also discounted by 50% and are applied automatically above.
| Models sharing the rate | Input | 5m write | 1h write | Cache read | Output | Batch input | Batch output |
|---|---|---|---|---|---|---|---|
| Fable 5.1; Mythos 5.1 limited access | $10 | $12.50 | $20 | $0.25 | $50 | $5 | $25 |
| Fable 5; Mythos 5 limited access | $10 | $12.50 | $20 | $1 | $50 | $5 | $25 |
| Opus 5.5 | $4 | $5 | $8 | $0.20 | $20 | $2 | $10 |
| Opus 5, 4.8, 4.7, 4.6, 4.5 | $5 | $6.25 | $10 | $0.50 | $25 | $2.50 | $12.50 |
| Sonnet 5.5 | $2 | $2.50 | $4 | $0.10 | $10 | $1 | $5 |
| Sonnet 5 | $2 | $2.50 | $4 | $0.20 | $10 | $1 | $5 |
| Sonnet 4.6, 4.5 | $3 | $3.75 | $6 | $0.30 | $15 | $1.50 | $7.50 |
| Haiku 5.5: prompt up to 100,000 tokens | $0.10 | $0.125 | $0.20 | $0.01 | $0.50 | $0.05 | $0.25 |
| Haiku 5.5: prompt over 100,000 tokens | $0.50 | $0.625 | $1 | $0.05 | $2.50 | $0.25 | $1.25 |
| Haiku 4.5 | $1 | $1.25 | $2 | $0.10 | $5 | $0.50 | $2.50 |
Fast uses $8 per million input tokens and $40 per million output tokens for Opus 5.5, or $10/$50 for Opus 5 and Opus 4.8. US-only inference multiplies each token rate by 1.1. The $0.01 successful web-search fee is not multiplied.
How to estimate your Claude API bill
- Choose the exact model and processing mode. Batch can reduce token charges when asynchronous processing suits the workload. Fast is limited to supported Opus models; access depends on the model and usage tier.
- Copy token counts from a representative API response. Keep uncached input, five-minute writes, one-hour writes, cache reads and output separate because Anthropic prices them differently.
- Enter the request volume. For a monthly forecast, use the number of calls expected in a typical month. Decimal web searches are accepted as an average per request.
- Compare the result with observed usage. Re-run the estimate after prompt, model or caching changes, then reconcile it with Anthropic’s usage and cost reports.
How Claude prompt caching changes cost
Claude reports uncached input, cache creation and cache reads as separate usage categories. A five-minute cache write costs 1.25 times the model’s base input rate and a one-hour write costs 2 times the base input rate. Most cache reads cost 0.1 times base input. Opus 5.5 and Sonnet 5.5 use 0.05 times base input for cache reads: $0.20 and $0.10 per million tokens respectively. Fable 5.1 and Mythos 5.1 use $0.25 per million, or 0.025 times base input. Other applicable pricing modifiers still apply.
The cache fields above are not subsets of uncached input. Anthropic defines total input as uncached input plus cache-creation input plus cache-read input. For the best forecast, copy the relevant values from the response usage object rather than estimating all prompt text as one input number.
Standard vs Batch vs Fast mode
- Standard uses the model’s normal token rates and suits synchronous requests.
- Batch applies the Message Batches API’s 50% token discount. Prompt-cache multipliers stack with Batch, while a successful web search still costs $0.01.
- Fast is available for Claude Opus 5.5, Opus 5 and Opus 4.8. Fast for Opus 5 and 4.8 remains in research preview. Opus 5.5 uses $8 per million input tokens and $40 per million output tokens; Opus 5 and 4.8 use $10/$50. These rates apply across the full context window. Prompt-cache and US-only multipliers still apply. For Opus 5.5, Start, Build and Scale accounts have default Fast access; Evaluation accounts need to move to one of those tiers. Check the official Fast-mode guide for model-specific access and rate limits. Fast cannot be combined with Batch or a Priority Tier commitment.
Does Claude charge more for long context?
Claude Haiku 5.5 has two price bands. A prompt of exactly 100,000 input tokens keeps the lower rates. Above 100,000, the higher rates apply to every token category for that request, including output. Prompt length includes uncached input, both cache-write categories and cache reads. Each request is assessed separately; monthly request volume does not change its band. Batch halves either band and US-only inference adds 10% to token charges. Other listed Claude 4.6 and later models include their full context window at their normal per-token rates.
Claude 4.7 and later use a newer tokenizer that Anthropic says may produce about 30% more tokens for the same text, depending on the workload. That is not a pricing multiplier. Use actual API usage when comparing old and new models.
Web search and other Claude tool charges
Anthropic lists web search at $10 per 1,000 successful searches, plus normal model tokens for search-generated content. Searches that return an error are not billed. Web search inside a Batch request has the same per-search charge.
Web fetch has no separate per-call fee, although fetched content still produces token charges. Code execution has organization-level free allowances and container-hour pricing that do not map cleanly to one request, so it is not included here. Client tools, bash, text editing and computer use generally add token or tool-definition overhead rather than one stable per-call fee.
What this estimate does not include
This calculator covers first-party Claude API token usage and successful web-search calls. It does not estimate claude.ai subscriptions, Amazon Bedrock, Claude Platform on AWS, Google Cloud, Microsoft Foundry, marketplace billing, Priority Tier, Claude Managed Agents, negotiated discounts, taxes, retries hidden by your application or surrounding infrastructure.
Claude API calculator FAQ
Is the Claude API included with a Claude Pro or Max subscription?
No. Consumer Claude subscriptions and first-party Claude API usage are separate products. This page estimates API usage, not subscription allowances.
How much does Claude Opus 5.5 cost?
Opus 5.5 costs $4 per million uncached input tokens and $20 per million output tokens for standard global API usage. Five-minute cache writes cost $5, one-hour writes cost $8 and cache reads cost $0.20 per million tokens. Batch halves those token rates. Fast uses $8 input and $40 output, with the model’s cache multipliers applied to those Fast rates.
How much does Claude Sonnet 5.5 cost?
Sonnet 5.5 standard global API rates are $2 per million input tokens and $10 per million output tokens. Five-minute cache writes cost $2.50, one-hour cache writes $4 and cache reads $0.10 per million tokens. Sonnet 5 remains separate with $0.20 cache reads. Batch halves token rates.
How much does Claude Haiku 5.5 cost?
For prompts up to 100,000 input tokens, Standard global rates per million tokens are $0.10 input, $0.125 five-minute cache writes, $0.20 one-hour cache writes, $0.01 cache reads and $0.50 output. Above 100,000 total input tokens, all five rates are five times higher. Batch halves the applicable rates. US-only inference multiplies token charges by 1.1. Fast is not available for Haiku 5.5.
How much does Claude Fable 5.1 cost?
For standard global API usage, Anthropic lists Fable 5.1 at $10 per million input tokens, $12.50 per million five-minute cache-write tokens, $20 per million one-hour cache-write tokens, $0.25 per million cache-read tokens and $50 per million output tokens. Fable 5 remains a separate model with a $1-per-million cache-read rate.
Does Batch reduce Claude prompt-cache pricing?
Yes. Anthropic says the 50% Message Batches discount and prompt-caching multipliers stack. Cache hits are best-effort in asynchronous batches, so estimate from observed usage where possible.
Does a one-million-token prompt cost extra?
Haiku 5.5 is the exception: prompts over 100,000 total input tokens use its higher input, cache and output rates for the whole request. The other listed Claude 4.6 and later models use normal per-token rates across their full context window. More tokens still increase the bill.
Why are cache writes and cache reads separate?
They have different rates. A five-minute cache write costs 1.25 times base input and a one-hour write costs 2 times base input. Cache reads normally cost 0.1 times base input. Opus 5.5 and Sonnet 5.5 use 0.05 times base input ($0.20 and $0.10 per million tokens respectively), while Fable 5.1 and Mythos 5.1 use 0.025 times base input ($0.25 per million tokens), before other applicable modifiers.
How much does Claude web search cost?
Anthropic lists web search at $10 per 1,000 successful searches, plus the model tokens consumed by search-generated content. Failed search calls are not billed.
Why can the estimate differ from my invoice?
Actual prompts, outputs, cache hits, retries, tool use and enterprise terms vary. Claude 4.7 and later also use a newer tokenizer that may produce more tokens for the same text than earlier models. Reconcile forecasts with the API usage and cost reports.
Sources and related calculators
This is an independent calculator, not an Anthropic product. Rates and compatibility were checked against Anthropic’s pricing documentation, Fable 5.1 model page, Opus 5.5 model page, models overview, Sonnet 5.5 announcement, prompt-caching guide, Batch guide, Fast-mode guide, data-residency guide and web-search documentation.
Compare providers with our AI API cost calculators, OpenAI API cost calculator and Gemini API cost calculator.