Claude API pricing (Anthropic)

As of November 14, 2026, the Claude API costs $0.1 to $10 per million input tokens and $0.5 to $50 per million output tokens, across 18 Claude models. Claude Haiku 5.5 costs $0.1 input and $0.5 output; Claude Sonnet 5.5 costs $2 input and $10 output; Claude Opus 5.5 costs $4 input and $20 output; Claude Fable 5.2 costs $8 input and $40 output; Claude Mythos 5.2 costs $8 input and $40 output. A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5 and $0.035 on Claude Mythos 5.1.

Prices updated

Claude API price per 1M tokens, every model

ModelInputCached inputCache writeOutputBatch inputBatch outputContextTypical request
Claude Haiku 5.5
claude-haiku-5-5
$0.1$0.01$0.125$0.5$0.05$0.251M$0.00035
Claude Haiku 4.5
claude-haiku-4-5
$1$0.1$1.25$5$0.5$2.5200K$0.0035
Claude Sonnet 5
claude-sonnet-5
$2$0.2$2.5$10$1$51M$0.007
Claude Sonnet 5.5
claude-sonnet-5-5
$2$0.1$2.5$10$1$51M$0.007
Claude Sonnet 4.5
claude-sonnet-4-5
$3$0.3$3.75$15$1.5$7.5200K$0.0105
Claude Sonnet 4.6
claude-sonnet-4-6
$3$0.3$3.75$15$1.5$7.51M$0.0105
Claude Opus 5.5
claude-opus-5-5
$4$0.2$5$20$2$101M$0.014
Claude Opus 4.5
claude-opus-4-5
$5$0.5$6.25$25$2.5$12.5200K$0.0175
Claude Opus 4.6
claude-opus-4-6
$5$0.5$6.25$25$2.5$12.51M$0.0175
Claude Opus 4.7
claude-opus-4-7
$5$0.5$6.25$25$2.5$12.51M$0.0175
Claude Opus 4.8
claude-opus-4-8
$5$0.5$6.25$25$2.5$12.51M$0.0175
Claude Opus 5
claude-opus-5
$5$0.5$6.25$25$2.5$12.51M$0.0175
Claude Fable 5.2
claude-fable-5-2
$8$0.2$10$40$4$201M$0.028
Claude Mythos 5.2
claude-mythos-5-2
$8$0.2$10$40$4$201M$0.028
Claude Fable 5
claude-fable-5
$10$1$12.5$50$5$251M$0.035
Claude Fable 5.1
claude-fable-5-1
$10$0.25$12.5$50$5$251M$0.035
Claude Mythos 5
claude-mythos-5
$10$1$12.5$50$5$251M$0.035
Claude Mythos 5.1
claude-mythos-5-1
$10$0.25$12.5$50$5$251M$0.035

US dollars per million tokens, sorted by the cost of a typical request of 1,000 input and 500 output tokens. Cache write is the standard (5-minute) cache.

Calculate the cost of your own prompt →

How much does a Claude API request cost?

A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5, $0.007 on Claude Sonnet 5.5, $0.014 on Claude Opus 5.5, $0.028 on Claude Fable 5.2 and $0.028 on Claude Mythos 5.2. A coding agent step with 50K tokens of context and 2K output tokens costs $0.48 on Claude Mythos 5.2.

ModelShort chat message
300 in, 200 out
Typical request
1K in, 500 out
Long document summary
20K in, 1K out
Coding agent step
50K in, 2K out
1,000 typical requests
Claude Haiku 5.5$0.00013$0.00035$0.0025$0.006$0.35
Claude Sonnet 5.5$0.0026$0.007$0.05$0.12$7.00
Claude Opus 5.5$0.0052$0.014$0.10$0.24$14.00
Claude Fable 5.2$0.0104$0.028$0.20$0.48$28.00
Claude Mythos 5.2$0.0104$0.028$0.20$0.48$28.00

At standard rates, for the newest model of each Claude family. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. Anthropic counts tokens with its own tokenizer, so the same text can be a different number of tokens.

How batch, prompt caching and long context change the price

Batch API. All 18 priced Claude models have a batch API price. Requests sent as a batch are processed within 24 hours and cost 50% less: Claude Mythos 5.2 drops from $8 input and $40 output to $4 and $20 per million tokens. See batch API pricing.

Prompt caching. All 18 priced Claude models charge less for cached input, the part of a prompt that repeats across requests: typically 90% less. Claude Mythos 5.2 charges $0.2 per million cached input tokens instead of $8. Writing a prompt to the cache costs extra: 1.25× the input price for the standard cache and 2× for the 1-hour cache (Claude Mythos 5.2: $10 and $16 per million tokens). The write pays for itself on the first request that reads the cache. See prompt caching pricing.

Long context. Claude models accept 200K to 1M input tokens. Long prompts cost more on one model: Claude Haiku 5.5 charges $0.5 input and $2.5 output per million tokens once a prompt is over 100K tokens, instead of $0.1 input and $0.5 output. A 200K-token prompt with 2K output tokens on Claude Haiku 5.5 costs $0.11, against $0.021 at the standard rate. The other 17 models list one price for their whole context window.

Anthropic API price changes

Since October 22, 2026, when apicost.app started tracking, no Anthropic model has changed its standard API price. 2 new models were added, most recently Claude Fable 5.2 on Nov 14, 2026.

Dated from the day a change reached the price list. Every provider: LLM API price changes.

Claude API vs OpenAI and Gemini

It depends on the model. The cheapest Claude model, Claude Haiku 5.5, costs $0.00035 per typical request; the cheapest OpenAI model, GPT-5 nano, costs $0.00025. Claude Mythos 5.2 ($0.028) is closest in price to GPT-6 Astra ($0.035): 1.3× the price.

Claude modelInput / outputTypical requestClosest OpenAI modelClosest Gemini model
Claude Haiku 5.5$0.1 / $0.5$0.00035GPT-6 Luna $0.1 / $0.5 · $0.00035 · about the sameGemini 2.5 Flash Lite $0.1 / $0.4 · $0.0003 · 1.2× cheaper
Claude Sonnet 5.5$2 / $10$0.007GPT-6 Sol $2 / $10 · $0.007 · about the sameGemini 4 Argon $2 / $10 · $0.007 · about the same
Claude Opus 5.5$4 / $20$0.014GPT-5.6 $4 / $20 · $0.014 · about the sameGemini 3.1 Pro Preview $2 / $12 · $0.008 · 1.8× cheaper
Claude Fable 5.2$8 / $40$0.028GPT-6 Astra $10 / $50 · $0.035 · 1.3× the priceGemini 3.1 Pro Preview $2 / $12 · $0.008 · 3.5× cheaper
Claude Mythos 5.2$8 / $40$0.028GPT-6 Astra $10 / $50 · $0.035 · 1.3× the priceGemini 3.1 Pro Preview $2 / $12 · $0.008 · 3.5× cheaper

For each Claude model, the model from the other provider whose typical request costs the nearest, with its input / output price per million tokens, its typical request, and how that compares with the Claude model.

Questions and answers

How much does the Claude API cost?

As of November 14, 2026, the Claude API costs $0.1 to $10 per million input tokens and $0.5 to $50 per million output tokens, across 18 Claude models. Claude Haiku 5.5 costs $0.1 input and $0.5 output; Claude Sonnet 5.5 costs $2 input and $10 output; Claude Opus 5.5 costs $4 input and $20 output; Claude Fable 5.2 costs $8 input and $40 output; Claude Mythos 5.2 costs $8 input and $40 output. A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5 and $0.035 on Claude Mythos 5.1.

Did Anthropic raise its API prices?

No. Since October 22, 2026, when apicost.app started tracking, no Anthropic model has changed its standard API price. 2 new models were added, most recently Claude Fable 5.2 on Nov 14, 2026.

What is the cheapest Claude model?

Claude Haiku 5.5 (claude-haiku-5-5), at $0.1 per million input tokens and $0.5 per million output tokens.

Is the Claude API free?

You pay per token: the Claude API is pay as you go, billed separately from any Claude subscription. The cheapest model, Claude Haiku 5.5, costs $0.1 per million input tokens and $0.5 per million output tokens, so 1,000 typical requests cost $0.35.

Is the Claude API cheaper than a Claude subscription?

It depends on how much you use it. $20 of Claude API usage pays for about 1,428 typical requests (1,000 input and 500 output tokens) on Claude Opus 5.5, or 57,142 on Claude Haiku 5.5. At 30 typical requests a day, a month costs $12.60 on Claude Opus 5.5 and $0.32 on Claude Haiku 5.5. Long chats cost more per message than that, because every turn sends the whole conversation again as input tokens. The API is billed separately from any Claude app subscription.

Why is the Claude API so expensive?

Mostly because of output tokens and long prompts. Claude Opus 5.5 charges 5× more for output ($20 per million tokens) than for input ($4). Reasoning models bill their thinking as output tokens, even though you don't see it. And a chat sends the whole conversation again as input on every turn, so a long chat gets more expensive with each message. To pay less: Claude Haiku 5.5 is 40× cheaper per typical request than Claude Opus 5.5, the batch API takes 50% off and cached input costs 90% less.

How much does a Claude API request cost?

A typical request of 1,000 input and 500 output tokens costs $0.00035 on Claude Haiku 5.5, $0.007 on Claude Sonnet 5.5, $0.014 on Claude Opus 5.5, $0.028 on Claude Fable 5.2 and $0.028 on Claude Mythos 5.2. A coding agent step with 50K tokens of context and 2K output tokens costs $0.48 on Claude Mythos 5.2.

Is the Claude batch API cheaper?

Yes. All 18 priced Claude models have a batch API price. Requests sent as a batch are processed within 24 hours and cost 50% less: Claude Mythos 5.2 drops from $8 input and $40 output to $4 and $20 per million tokens.

How much does prompt caching save on the Claude API?

All 18 priced Claude models charge less for cached input, the part of a prompt that repeats across requests: typically 90% less. Claude Mythos 5.2 charges $0.2 per million cached input tokens instead of $8. Writing a prompt to the cache costs extra: 1.25× the input price for the standard cache and 2× for the 1-hour cache (Claude Mythos 5.2: $10 and $16 per million tokens). The write pays for itself on the first request that reads the cache.

Does long context cost more on the Claude API?

Yes, on some models. Claude models accept 200K to 1M input tokens. Long prompts cost more on one model: Claude Haiku 5.5 charges $0.5 input and $2.5 output per million tokens once a prompt is over 100K tokens, instead of $0.1 input and $0.5 output. A 200K-token prompt with 2K output tokens on Claude Haiku 5.5 costs $0.11, against $0.021 at the standard rate. The other 17 models list one price for their whole context window.

Is the Claude API cheaper than OpenAI?

It depends on the model. The cheapest Claude model, Claude Haiku 5.5, costs $0.00035 per typical request; the cheapest OpenAI model, GPT-5 nano, costs $0.00025. Claude Mythos 5.2 ($0.028) is closest in price to GPT-6 Astra ($0.035): 1.3× the price.

Is the Claude API included in a Claude Pro or Max subscription?

No. Claude Pro and Max cover the Claude apps. The Claude API is billed separately, pay as you go per token, through the Claude Console at the prices on this page.

Source: Anthropic pricing, via the LiteLLM price list.

Other providers

OpenAI API pricingGemini API pricing (Google)Mistral API pricingDeepSeek API pricingGrok API pricing (xAI)