LPLLM Price Calc Independent tool

CLAUDE API · VERIFIED OCTOBER 8, 2026

Claude API
Pricing

Compare current list prices for the Claude 5.5 family. Prices are USD per one million tokens on the Claude Platform; provider-specific rates can differ.

BALANCED

Sonnet 5.5

claude-sonnet-5-5
INPUT / MTOK$2.00
OUTPUT / MTOK$10.00

Cache read $0.10 · five-minute cache write $2.50.

MOST CAPABLE

Opus 5.5

claude-opus-5-5
INPUT / MTOK$4.00
OUTPUT / MTOK$20.00

Cache read $0.20 · five-minute cache write $5.00. Fast mode costs more.

01 / COST ESTIMATOR

Estimate a Claude API workload.

Choose a model and enter monthly token volume. The estimate uses the displayed list rates and runs entirely in your browser.

Estimated monthly token cost$2.00Before cache, batch, regional or provider-specific adjustments.
01 / QUICK DECISION

Choose for the workload, not only the token rate.

A cheaper model may use a different number of tokens or need more retries. Test on your own workload.

Choose Haiku

For high-volume summarization, classification, routing, compaction and real-time experiences where speed and unit cost matter.

Choose Sonnet

For well-scoped coding, agents and everyday production work that needs a stronger balance of capability, latency and price.

Choose Opus

For complex, long-running work where judgment and reliability matter more than the lowest token cost.

03 / REAL COST SCENARIOS

Translate token prices into product decisions.

Support classification

10M input and 2M output tokens cost about $2 on the listed Haiku short-tier rates, before caching or batch discounts.

Production coding agent

The same volume costs about $40 on Sonnet. Track retries and accepted patches because task cost matters more than price per token.

Complex research

The same volume costs about $80 on Opus. Reserve the higher rate for tasks where stronger judgment reduces costly failures.

04 / FAQ

Claude API pricing questions

How is Claude API cost calculated?

Multiply input and output token counts by their respective per-million-token rates, then add cache and provider-specific charges.

Which Claude model is cheapest?

Haiku has the lowest displayed token rates. The cheapest model per completed task can differ when retries, output length and quality requirements are included.

Does prompt caching reduce Claude cost?

It can reduce repeated-input cost when the workload meets the provider’s caching rules. Cache writes and reads have separate rates.

Are AWS Bedrock and Vertex AI prices identical?

Do not assume so. Verify the rate card for the exact platform and region you deploy to.

How often should I verify API prices?

Check the official provider page before launch and whenever a model, context tier or hosting route changes.

Calculate a real Haiku 5.5 workload.

Include prompt length, caching, Batch API and monthly request volume.

Open calculator →