Claude Haiku 4.5
by AnthropicReleased Oct 15, 2025
anthropic/claude-haiku-4.5- Reads images
- Reads files and PDFs
- Calls tools
- Answers in a JSON schema
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
- Input / 1M tokens
- $1.20
- Output / 1M tokens
- $6.00
- Context
- 200K
- Longest answer
- 64K
What it costs
What each call is charged to the token's AI credit.
| Billed for | You pay |
|---|---|
| Input tokens | $1.20 / 1M |
| Output tokens | $6.00 / 1M |
| Cached input, read | $0.12 / 1M |
| Cached input, written | $1.50 / 1M |
| Each web search | $0.01 |
A typical call
A short chat turn: 2,000 tokens in, 500 out.
- per call
- $0.0054
- calls per $20
- 3,703
What it can do
From its listing. The router passes every field through.
- Reads imagesYes
- Reads files and PDFsYes
- Hears audioNo
- Calls toolsYes
- Answers in a JSON schemaYes
- Reasons before it answersYes
- Searches the webYes
- Caches long promptsYes
- Draws imagesNo
Call it
Any router key works, in the format your SDK already speaks.
import OpenAI from "openai";const ai = new OpenAI({ baseURL: "https://relayfor.si/api/v1", apiKey: process.env.RELAYFOR_ROUTER_KEY,});const reply = await ai.chat.completions.create({ model: "anthropic/claude-haiku-4.5", messages: [{ role: "user", content: "Welcome the 1,000th holder in one line." }],});Specifications
What its maker and providers list for it.
- Reads
- Text, Images, and Files
- Writes
- Text
- Context
- 200,000 tokens
- Longest answer
- 64,000 tokens
- Intelligence index
- 16.9 (#109 of 219 rated)
- Released
- Oct 15, 2025
- Moderation
- Screened
Request fields
The fields its providers accept, passed through as you send them.
- include_reasoning
- max_completion_tokens
- max_tokens
- reasoning
- response_format
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_p
Questions
How much does Claude Haiku 4.5 cost?
$1.20 per million input tokens and $6.00 per million output tokens, paid from the token's AI credit. A call of 2,000 tokens in and 500 out costs about $0.0054.
How do I call Claude Haiku 4.5?
Make a router key for one of your tokens on the dashboard, point any OpenAI or Anthropic SDK at https://relayfor.si/api/v1 and send the model id anthropic/claude-haiku-4.5. The token's AI credit pays for each call.
How long a prompt can Claude Haiku 4.5 take?
Up to 200,000 tokens of context, and up to 64,000 tokens in one answer.
Are my prompts stored?
No. The RFS Router passes each call through and keeps only its token counts and cost, for the token's usage page.
More from Anthropic
Output price per 1M tokens
Similar in price
Output price per 1M tokens
