Claude API pricing in 2026: every model, current rates

Prices verified August 21, 2026 · USD per 1M tokens

Anthropic prices the Claude API per million tokens, with separate input and output rates. As of August 2026 the lineup spans four tiers, from Haiku for high-volume light work to Fable 5, the frontier model. All tiers support prompt caching (~90% off repeated input) and a 50% Batch API discount.

ModelInputCached inputOutputContext
Claude Fable 5$10.00$1.00$50.001M
Claude Opus 5$5.00$0.50$25.001M
Claude Sonnet 5 *$2.00$0.20$10.001M
Claude Haiku 4.5$1.00$0.10$5.00200K

* Sonnet 5 promotional rate through August 31, 2026; standard rate $3 input / $15 output. Cache hits bill at 10% of input; Batch API takes 50% off both directions.

Which Claude model should you pay for?

Sonnet 5 is the default for production apps — near-flagship quality at 1/5th the frontier price, and the promo rate makes August an especially good month to lock in usage. Haiku 4.5 handles classification, extraction and routing at a fifth of Sonnet's price. Opus 5 and Fable 5 earn their premium on hard reasoning and agentic coding, where fewer retries can beat a cheaper per-token rate — measure per-task cost, not per-token.

Three ways to cut your Claude bill

First, prompt caching: mark your stable system prompt with cache_control and repeated input bills at 10%. A chatbot with a 3K-token system prompt saves ~50% overall. Second, the Batch API: 50% off everything if you can wait for async results. Third, right-size the model — run an eval on Haiku before assuming you need Sonnet. Details with worked math in our caching guide and Claude vs GPT comparison.

→ What would YOUR workload cost?
Enter your token mix once — compare all 28 models side by side, with caching and batch discounts.
Advertisement

Frequently asked questions

How much does the Claude API cost in 2026?
As of August 2026: Claude Fable 5 costs $10 input / $50 output per million tokens, Claude Opus 5 $5/$25, Claude Sonnet 5 $2/$10 (promotional; standard $3/$15), and Claude Haiku 4.5 $1/$5.
Is there a free tier for the Claude API?
Anthropic offers limited free evaluation credits for new API accounts, but sustained usage is pay-as-you-go. The claude.ai consumer app has a free plan, but that is separate from API pricing.
How much does Claude prompt caching save?
Cache hits bill at 10% of the normal input rate — e.g. $0.20 instead of $2.00 per million tokens on Sonnet 5. For chatbots with large stable system prompts, total savings of 40–60% are typical.
What is the cheapest Claude model?
Claude Haiku 4.5 at $1 input / $5 output per million tokens. For a typical chatbot request (500 in / 300 out) that is about $0.002 per request.
Do Claude API prices include the Batch API discount?
No — batch is a separate 50% discount on both input and output for asynchronous processing, and it can be combined with caching in many cases.