Claude API pricing: what Anthropic charges per 1M tokens
Input, output, cache-write and cache-hit prices for every current Claude model, batch and long-context rates, the extras that add to the bill, and a worked monthly cost example.
Last updated October 22, 2026
How much does the Claude API cost?
On October 22, 2026, Anthropic charged $10 per 1M input tokens and $50 per 1M output tokens for Claude Fable 5.1, $4 and $20 for Claude Opus 5.5, $2 and $10 for Claude Sonnet 5.5, and from $0.10 and $0.50 for Claude Haiku 5.5. The Batch API halves these prices and cache hits cost far less.
What does each Claude model cost per 1M tokens?
These are the standard prices for the four models in Anthropic’s current lineup, from its pricing page. Anthropic’s models overview suggests starting with Claude Opus 5.5 for most workloads and using Claude Fable 5.1 for the most demanding reasoning and long-horizon agentic work.
| Model | Base input | 5-min cache write | 1-hour cache write | Cache hits and refreshes | Output |
|---|---|---|---|---|---|
| Claude Fable 5.1 | $10 | $12.50 | $20 | $0.25 | $50 |
| Claude Opus 5.5 | $4 | $5 | $8 | $0.20 | $20 |
| Claude Sonnet 5.5 | $2 | $2.50 | $4 | $0.10 | $10 |
| Claude Haiku 5.5 (prompts up to 100,000 tokens) | $0.10 | $0.125 | $0.20 | $0.01 | $0.50 |
| Claude Haiku 5.5 (prompts over 100,000 tokens) | $0.50 | $0.625 | $1 | $0.05 | $2.50 |
Prices checked October 22, 2026. Providers change prices often; confirm on Anthropic’s pricing page.
Older models Anthropic still lists as available (legacy) keep their own prices on the same page: Claude Fable 5 at $10 / $50, Claude Opus 5, 4.8, 4.7, 4.6 and 4.5 at $5 / $25, Claude Sonnet 5 at $2 / $10, Claude Sonnet 4.6 at $3 / $15 and Claude Haiku 4.5 at $1 / $5 per 1M input / output tokens. Claude Mythos 5.1 is priced like Fable 5.1 but is available only to organizations verified through Anthropic’s access programs.
How does Claude API billing work?
- Input and output tokens are billed separately. Input covers the system prompt, the conversation, documents and images you send, and tool definitions; output is what Claude generates.
- Tool use adds tokens. When you pass tools, Anthropic adds a tool-use system prompt (286 tokens on Claude Opus 5.5, for example) plus your tool names, descriptions and schemas, all billed as input.
- Some tools cost extra. Web search is $10 per 1,000 searches plus the tokens it returns; web fetch has no charge beyond tokens.
- Token counts depend on the model. Anthropic says Claude 4.7 and later models use a tokenizer that produces roughly 30% more tokens for the same text than earlier models, so moving from an older model can raise token counts.
- Where data is processed can change the price. Choosing US-only inference with
inference_geoon Claude 4.6 and later models applies a 1.1× multiplier to all token prices. - Fast mode costs more. On Claude Opus 5.5, fast mode is $8 per 1M input tokens and $40 per 1M output tokens.
What would 1M requests a month cost on Claude?
Take 1,000,000 requests a month, each with 1,000 input tokens and 300 output tokens: 1,000M input tokens and 300M output tokens, with no caching. Every prompt is under 100,000 tokens, so Haiku 5.5 uses its lower rate.
Monthly cost = 1,000 × input price + 300 × output price (prices per 1M tokens)
| Model and tier | Calculation | Monthly cost |
|---|---|---|
| Claude Fable 5.1, standard | 1,000 × $10 + 300 × $50 | $25,000 |
| Claude Opus 5.5, standard | 1,000 × $4 + 300 × $20 | $10,000 |
| Claude Sonnet 5.5, standard | 1,000 × $2 + 300 × $10 | $5,000 |
| Claude Sonnet 5.5, Batch API | 1,000 × $1 + 300 × $5 | $2,500 |
| Claude Haiku 5.5, standard | 1,000 × $0.10 + 300 × $0.50 | $250 |
Your real token counts will differ, especially with tools or long system prompts. Count them with the token calculator, and remember the tokenizer note above when comparing Claude with other providers.
How can you cut your Claude API bill?
| Model | Batch input | Batch output |
|---|---|---|
| Claude Fable 5.1 | $5 | $25 |
| Claude Opus 5.5 | $2 | $10 |
| Claude Sonnet 5.5 | $1 | $5 |
| Claude Haiku 5.5 (prompts up to 100,000 tokens) | $0.05 | $0.25 |
| Claude Haiku 5.5 (prompts over 100,000 tokens) | $0.25 | $1.25 |
Prices checked October 22, 2026. Providers change prices often; confirm on Anthropic’s pricing page.
- Batch API. Anthropic’s batch processing runs requests asynchronously at 50% off both input and output. Fast mode is not available with batch.
- Prompt caching. With prompt caching, a cache hit costs 10% of the base input price on most models, 5% on Claude Opus 5.5 and Claude Sonnet 5.5, and 2.5% on Claude Fable 5.1. A 5-minute write costs 1.25× input and a 1-hour write 2×, so Anthropic says caching pays off after one read for 5-minute writes and after two reads for 1-hour writes. Caching and batch discounts stack.
- Smaller models. Anthropic’s own cost advice is to use Haiku for simple tasks, Sonnet for most production workloads and Opus for the most complex reasoning. Claude Haiku 5.5 costs 1/40 of Claude Opus 5.5 per token on prompts up to 100,000 tokens.
- Volume discounts. Anthropic says volume discounts may be negotiated case by case for high-volume users.
To estimate what response caching and model routing could add on top, try the LLM gateway savings calculator.
How does Perimattic LLM Gateway help with Claude costs?
Perimattic LLM Gateway sits between your application and model providers. Its features:
- One OpenAI-compatible API in front of Anthropic, OpenAI, Google, Mistral, DeepSeek and open models.
- Routing rules that send each request to a model by cost, latency or task, for example Haiku for simple requests and Opus for hard ones, with automatic fallback when a provider errors or rate-limits.
- Exact-match and semantic caching of responses.
- Budgets and rate limits per team, API key or customer, with cost tracking and alerts.
Get started: Sign up and our team will walk you through Perimattic LLM Gateway for your workloads.
Where do these Claude prices come from?
All prices on this page come from Anthropic’s Claude API pricing page, with model status from its models overview; Anthropic also publishes prices at claude.com/pricing. They are Anthropic’s direct API prices in US dollars, before tax; Amazon Bedrock and Google Cloud set their own prices for Claude. Prices checked October 22, 2026; providers change prices often — confirm on the provider’s page before you rely on them. Perimattic is not affiliated with Anthropic.
Compare Claude with other providers
Claude API pricing, answered
Is Anthropic API pricing the same as Claude API pricing?
Yes. Anthropic sells API access to its Claude models, so “Anthropic API pricing” and “Claude API pricing” refer to the same price list. Claude models are also sold through Amazon Bedrock and Google Cloud, which set their own prices, so check those providers’ pages if you buy Claude there.
Does a long prompt cost more on Claude?
On most current models, no. Anthropic’s pricing page says Claude 4.6 and later models, except Claude Haiku 5.5, include the full 1M-token context window at standard prices. Claude Haiku 5.5 is the exception: a request whose prompt is over 100,000 tokens pays the higher rates for the whole request.
Is there a free tier for the Claude API?
Anthropic’s pricing page says new users receive a small amount of free credits to test the API, and that enterprise customers can contact sales about extended trials. After that, usage is billed monthly in US dollars by actual usage.
Want one API for every model, with costs under control?
Sign up to tell us which models and providers you use, and our team will get in touch to set up the LLM Gateway for your stack.
Sign up