GVGanivra

Anthropic API pricing · Updated

Claude API pricing

Quick answer

Claude API prices range from $0.10 per million input tokens on Claude Haiku 5.5 to $10.00 on Claude Fable 5.1. Per million input and output tokens, Haiku 5.5 costs $0.10 and $0.50, Sonnet 5.5 $2.00 and $10.00, Opus 5.5 $4.00 and $20.00, and Fable 5.1 $10.00 and $50.00. The Batch API halves every price, and cached input costs 2.5% to 10% of the input price.

Estimate your monthly Claude API cost

Estimated monthly cost$1,100$0.011 per request on Claude Sonnet 5.5. Excludes cache writes, tools and taxes.

Claude API prices per million tokens

ModelInputCache read5-min cache writeOutputBatch in / outStatus
Fable and Mythos
Claude Fable 5.1claude-fable-5-1$10.00$0.25$12.50$50.00$5.00 / $25.00Active
Claude Mythos 5.1claude-mythos-5-1Limited availability$10.00$0.25$12.50$50.00$5.00 / $25.00Active
Claude Fable 5claude-fable-5$10.00$1.00$12.50$50.00$5.00 / $25.00Active
Claude Mythos 5claude-mythos-5Limited availability$10.00$1.00$12.50$50.00$5.00 / $25.00Active
OpusAll Opus prices →
Claude Opus 5.5claude-opus-5-5$4.00$0.20$5.00$20.00$2.00 / $10.00Active
Claude Opus 5claude-opus-5$5.00$0.50$6.25$25.00$2.50 / $12.50Active
Claude Opus 4.8claude-opus-4-8$5.00$0.50$6.25$25.00$2.50 / $12.50Active
Claude Opus 4.7claude-opus-4-7$5.00$0.50$6.25$25.00$2.50 / $12.50Active
Claude Opus 4.6claude-opus-4-6$5.00$0.50$6.25$25.00$2.50 / $12.50Active
Claude Opus 4.5claude-opus-4-5$5.00$0.50$6.25$25.00$2.50 / $12.50Active
SonnetAll Sonnet prices →
Claude Sonnet 5.5claude-sonnet-5-5$2.00$0.10$2.50$10.00$1.00 / $5.00Active
Claude Sonnet 5claude-sonnet-5$2.00$0.20$2.50$10.00$1.00 / $5.00Active
Claude Sonnet 4.6claude-sonnet-4-6$3.00$0.30$3.75$15.00$1.50 / $7.50Active
Claude Sonnet 4.5claude-sonnet-4-5$3.00$0.30$3.75$15.00$1.50 / $7.50Deprecated, shuts down November 30, 2026
Haiku
Claude Haiku 5.5claude-haiku-5-5Prompts over 100,000 tokens: $0.50 in / $2.50 out$0.10$0.01$0.125$0.50$0.05 / $0.25Active
Claude Haiku 4.5claude-haiku-4-5$1.00$0.10$1.25$5.00$0.50 / $2.50Active

Prices from Anthropic’s pricing page and deprecation schedule, for Anthropic’s own API. Retired models such as Opus 4.1 and Sonnet 4 are on the Opus and Sonnet pages. Upcoming changes across providers are on the price change and shutdown tracker.

What one request costs on each Claude API model

Worked out from the prices above for Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5 and Claude Haiku 5.5, at standard rates with no Batch discount.

RequestClaude Fable 5.1Claude Opus 5.5Claude Sonnet 5.5Claude Haiku 5.5
Chat reply3,000 input tokens, 500 output$0.055$0.022$0.011$0.0006
Document summary30,000 input tokens, 1,500 output$0.375$0.150$0.075$0.0037
Agent task80,000 input tokens (60,000 cached), 6,000 output$0.515$0.212$0.106$0.0056

Head-to-head price comparisons: Claude Sonnet 5.5 vs GPT-6.1 Sol · Claude Opus 5.5 vs GPT-6 Astra · Claude Opus 5.5 vs GPT-6.1 Sol · Claude Fable 5.1 vs GPT-6 Astra · Claude Haiku 5.5 vs GPT-6 Luna · Claude Sonnet 5.5 vs Gemini 4 Argon · Claude Opus 5.5 vs Gemini 4 Argon · Claude Sonnet 5.5 vs GPT-6.1 Terra · Gemini 3.8 Flash vs Claude Haiku 5.5 · Gemini 3.5 Flash-Lite vs Claude Haiku 5.5 · Claude Sonnet 5.5 vs DeepSeek V4.1 Flash · Claude Opus 5.5 vs Claude Sonnet 5.5 · Claude Sonnet 5.5 vs Claude Haiku 5.5 · Claude Fable 5.1 vs Claude Opus 5.5 · all comparisons.

Claude API discounts and extra charges

Batch API
50% off input and output on every model, for requests processed asynchronously. Combines with prompt caching.
Prompt caching
Cache reads cost 0.1× the input price on most models, 0.05× on Opus 5.5 and Sonnet 5.5, and 0.025× on Fable 5.1 and Mythos 5.1. Cache writes cost 1.25× for 5 minutes or 2× for 1 hour.
Fast mode
Faster output on Opus 5.5 ($8 input, $40 output), Opus 5 and Opus 4.8 ($10 and $50). Not available with the Batch API.
Long context
Claude 4.6 and later models include the 1M-token context window at standard prices, except Haiku 5.5, which charges more for prompts over 100,000 tokens.
New tokenizer
Claude 4.7 and later models, including Sonnet 5 and 5.5, turn the same text into about 30% more tokens than earlier models. Compare costs per request, not only per token.
US-only inference
Setting inference_geo to "us" multiplies every price by 1.1× on Claude 4.6 and later models.
Web search
$10 per 1,000 searches, plus the tokens the results add to the conversation. Web fetch has no charge beyond tokens.
Code execution
1,550 free container hours per organization per month, then $0.05 per hour. Free when used together with web search or web fetch.
Managed Agents
Tokens at the model prices above, plus $0.08 per session-hour while a session is running.
Bedrock, Google Cloud and Foundry
Partner clouds set their own prices. Regional and multi-region endpoints cost 10% more than global ones for Claude 4.5 and later models.

Your Anthropic bill shows the total. Ganivra shows it per customer.

Ganivra prices every Anthropic call at these rates and adds it up by customer, feature and workflow, next to what each customer pays. You see who is profitable and who isn’t.

Start free 14-day trial

Claude API pricing questions

How much does the Claude API cost?

It depends on the model. Per million tokens, Claude Haiku 5.5 costs $0.10 input and $0.50 output, Sonnet 5.5 $2.00 input and $10.00 output, Opus 5.5 $4.00 input and $20.00 output, and Fable 5.1 $10.00 input and $50.00 output. A chat reply of 3,000 input and 500 output tokens costs $0.0006 on Haiku 5.5 and $0.011 on Sonnet 5.5.

What is the cheapest Claude model?

Claude Haiku 5.5, at $0.10 input and $0.50 output per million tokens for prompts up to 100,000 tokens. Longer prompts cost $0.50 input and $2.50 output. With the Batch API it drops to $0.05 input.

What is the most expensive Claude model?

Claude Fable 5.1 and Claude Mythos 5.1, at $10.00 input and $50.00 output per million tokens. Mythos 5.1 has limited availability. Their cache reads cost $0.25 per million, the lowest share of the input price of any Claude model.

Is there a free tier for the Claude API?

There is no ongoing free tier. New accounts get a small amount of free credit for testing, and after that every token is billed at the prices on this page. Anthropic sales can arrange extended trials for enterprise evaluations.

Do Batch and prompt caching discounts stack?

Yes. The Batch API halves every price, including cache reads, so a cached input token on Sonnet 5.5 in a batch costs $0.05 per million instead of $2.00.

Why did my Claude bill go up after switching models?

Claude 4.7 and later models use a newer tokenizer that counts about 30% more tokens for the same text. A model with a lower price per token can still cost more per request, so compare the cost of real requests, not only the price list.

Which Claude models are being retired?

Claude Sonnet 4.5 retires on the Claude API on November 30, 2026; Anthropic recommends Sonnet 5.5 instead. Opus 4, Opus 4.1 and Sonnet 4 have already shut down on the Claude API, though some cloud platforms still serve them.

Is Claude cheaper on AWS Bedrock or Google Cloud?

Amazon Bedrock and Google Cloud set and publish their own Claude prices and bill you directly, so check their price lists. For Claude 4.5 and later models, their regional and multi-region endpoints cost 10% more than global endpoints. On the Claude API, keeping inference in the US costs 1.1×.

Does the Claude API charge more for long prompts?

Not on Claude 4.6 and later models: the 1M-token context window is billed at standard prices. The exception is Haiku 5.5, which charges $0.50 input and $2.50 output per million tokens once a prompt passes 100,000 tokens.

How do I track Claude API cost per customer?

Tag each Claude call with the customer it served, then price it at these rates and add it up by customer. Ganivra does this automatically with two lines of the Python SDK, and shows each customer's Claude cost next to what they pay you.

More detail: Claude Opus pricing · Claude Sonnet pricing · OpenAI API pricing · Gemini API pricing · all supported models and prices.