How much does the Claude API cost?
Every Claude model we track, per 1M tokens. Batch prices are half the standard rate.
| Model | Input | Cached input | Output | Batch input | Batch output | Context |
|---|---|---|---|---|---|---|
| Claude Fable 5.1 | $10.00 | $0.25 | $50.00 | $5.00 | $25.00 | 1M |
| Claude Opus 5.5 | $4.00 | $0.20 | $20.00 | $2.00 | $10.00 | 1M |
| Claude Sonnet 5.5 | $2.00 | $0.10 | $10.00 | $1.00 | $5.00 | 1M |
| Claude Haiku 5.5 | $0.10 | $0.01 | $0.50 | $0.05 | $0.25 | 1M |
| Claude Fable 5 | $10.00 | $1.00 | $50.00 | $5.00 | $25.00 | 1M |
| Claude Opus 5 | $5.00 | $0.50 | $25.00 | $2.50 | $12.50 | 1M |
| Claude Sonnet 5 | $2.00 | $0.20 | $10.00 | $1.00 | $5.00 | 1M |
| Claude Opus 4.8 | $5.00 | $0.50 | $25.00 | $2.50 | $12.50 | 1M |
| Claude Opus 4.7 | $5.00 | $0.50 | $25.00 | $2.50 | $12.50 | 1M |
| Claude Opus 4.6 | $5.00 | $0.50 | $25.00 | $2.50 | $12.50 | 1M |
| Claude Sonnet 4.6 | $3.00 | $0.30 | $15.00 | $1.50 | $7.50 | 1M |
| Claude Opus 4.5 | $5.00 | $0.50 | $25.00 | $2.50 | $12.50 | 200K |
| Claude Sonnet 4.5 retires 30 Nov 2026 | $3.00 | $0.30 | $15.00 | $1.50 | $7.50 | 200K |
| Claude Haiku 4.5 | $1.00 | $0.10 | $5.00 | $0.50 | $2.50 | 200K |
From Anthropic's pricing page, checked 6 Nov 2026. See all LLM API prices for the other 6 providers.
Which Claude model is cheapest for a typical workload?
Of the models we track, Claude Haiku 5.5, at $1.05 a month for 1,000 input and 500 output tokens a request, 100 requests a day. The same traffic costs $105.00 on Claude Fable 5. Every model, cheapest first:
| Model | Per request | Per month | Per month, batch |
|---|---|---|---|
| Claude Haiku 5.5 | $0.00035 | $1.05 | $0.525 |
| Claude Haiku 4.5 | $0.0035 | $10.50 | $5.25 |
| Claude Sonnet 5.5 | $0.007 | $21.00 | $10.50 |
| Claude Sonnet 5 | $0.007 | $21.00 | $10.50 |
| Claude Sonnet 4.6 | $0.0105 | $31.50 | $15.75 |
| Claude Sonnet 4.5 retires 30 Nov 2026 | $0.0105 | $31.50 | $15.75 |
| Claude Opus 5.5 | $0.014 | $42.00 | $21.00 |
| Claude Opus 5 | $0.0175 | $52.50 | $26.25 |
| Claude Opus 4.8 | $0.0175 | $52.50 | $26.25 |
| Claude Opus 4.7 | $0.0175 | $52.50 | $26.25 |
| Claude Opus 4.6 | $0.0175 | $52.50 | $26.25 |
| Claude Opus 4.5 | $0.0175 | $52.50 | $26.25 |
| Claude Fable 5.1 | $0.035 | $105.00 | $52.50 |
| Claude Fable 5 | $0.035 | $105.00 | $52.50 |
Why can a newer Claude model cost more for the same text?
Claude 4.7 and later models use a tokenizer that turns the same English text into about 30% more tokens. Claude Opus 4.7 and Claude Opus 4.6 both list $5.00 per 1M input tokens, yet the same document costs about 30% more to send to Claude Opus 4.7. The table below puts every model on one scale: estimated price per 1M characters of English text.
These are estimates from Anthropic's published ratio, so run your own prompt through the Claude token counter before you compare two models on cost.
| Model | Characters per token | Input per 1M tokens | Input per 1M characters | Output per 1M characters |
|---|---|---|---|---|
| Claude Fable 5.1 | 2.7 | $10.00 | $3.70 | $18.52 |
| Claude Opus 5.5 | 2.7 | $4.00 | $1.48 | $7.41 |
| Claude Sonnet 5.5 | 2.7 | $2.00 | $0.74 | $3.70 |
| Claude Haiku 5.5 | 2.7 | $0.10 | $0.037 | $0.19 |
| Claude Fable 5 | 2.7 | $10.00 | $3.70 | $18.52 |
| Claude Opus 5 | 2.7 | $5.00 | $1.85 | $9.26 |
| Claude Sonnet 5 | 2.7 | $2.00 | $0.74 | $3.70 |
| Claude Opus 4.8 | 2.7 | $5.00 | $1.85 | $9.26 |
| Claude Opus 4.7 | 2.7 | $5.00 | $1.85 | $9.26 |
| Claude Opus 4.6 | 3.5 | $5.00 | $1.43 | $7.14 |
| Claude Sonnet 4.6 | 3.5 | $3.00 | $0.86 | $4.29 |
| Claude Opus 4.5 | 3.5 | $5.00 | $1.43 | $7.14 |
| Claude Sonnet 4.5 | 3.5 | $3.00 | $0.86 | $4.29 |
| Claude Haiku 4.5 | 3.5 | $1.00 | $0.29 | $1.43 |
What do caching and batch save on Claude?
Cached input costs 10% of the input price on 11 models, 2.5% on Claude Fable 5.1 and 5% on Claude Opus 5.5 and Claude Sonnet 5.5. So Claude Fable 5.1 reads a cached prompt at $0.25 per 1M tokens against $10.00 for fresh input.
Writing to the cache costs extra: 1.25 times the input price for a 5-minute cache, 2 times for a 1-hour cache. By Anthropic's own math, the 5-minute cache pays for itself after one read and the 1-hour cache after two.
The Batch API takes 50% off input and output, and the discount stacks with caching. On Claude Sonnet 5.5, the example workload costs $21.00 a month at list price and $10.50 as a batch job.
Two surcharges to plan around. Claude Haiku 5.5 charges $0.50 in and $2.50 out per 1M once a prompt passes 100K input tokens, five times its normal rate. Asking for US-only inference multiplies every price by 1.1.
Which Claude models are being retired?
Anthropic retires Claude Sonnet 4.5 on 30 Nov 2026. Requests to a retired model fail, so move before the date. Claude Sonnet 5.5 is the current Sonnet at $2.00 in and $10.00 out, against $3.00 and $15.00 for Claude Sonnet 4.5, though its newer tokenizer narrows the gap per character (see the table above).
Is the Claude API free?
Only for a small trial. Anthropic does not say how big the credit is, and once it runs out you have to buy credits before any call. Claude Haiku 5.5 is the cheapest current model at $0.10 in and $0.50 out, and runs the example workload for $1.05 a month. Read is the Claude API free for the trial terms, or see which free LLM APIs have no time limit.
How does Claude API pricing compare with OpenAI and Gemini?
The budget, flagship and top models from each provider on the same example workload, cheapest first. Claude rows are highlighted. For the full price lists, see OpenAI API pricing and Gemini API pricing.
| Model | Provider | Input | Output | Example month |
|---|---|---|---|---|
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | $1.05 |
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $1.05 |
| Gemini 3.5 Flash Lite | $0.30 | $2.50 | $4.65 | |
| GPT-6.1 Sol | OpenAI | $2.00 | $10.00 | $21.00 |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $10.00 | $21.00 |
| Gemini 4 Argonpromo to 30 Nov | $2.00 | $10.00 | $21.00 | |
| GPT-6 Astra | OpenAI | $10.00 | $50.00 | $105.00 |
| Claude Fable 5.1 | Anthropic | $10.00 | $50.00 | $105.00 |
Frequently asked
How much does the Claude API cost per 1M tokens?
From $0.10 input and $0.50 output (Claude Haiku 5.5) to $10.00 input and $50.00 output (Claude Fable 5.1). Claude Opus 5.5 is $4.00 and $20.00, and Claude Sonnet 5.5 is $2.00 and $10.00. Checked 6 Nov 2026.
Which Claude model is cheapest?
Of the 14 Claude models we track, Claude Haiku 5.5, at $0.10 per 1M input and $0.50 per 1M output tokens for prompts up to 100K tokens. The example workload of 100 requests a day costs $1.05 a month on it.
Is Claude Sonnet 5.5 cheaper than Sonnet 4.6?
Per token, yes: $2.00 and $10.00 against $3.00 and $15.00. Per character the gap is smaller, because Claude Sonnet 5.5 uses the newer tokenizer: an estimated $0.74 per 1M characters of input against $0.86.
Does Anthropic charge for batch requests?
Yes, at half price. The Batch API bills 50% of the normal input and output rate for requests that can wait, and the batch columns above show those prices for every Claude model. Cache discounts apply on top.