AnthropicFastHigh

Claude Haiku 5.5

Anthropic's newest Haiku model (October 2026), the fast, low-cost choice for high-volume work such as classification, routing, extraction, and sub-agent tasks. $0.10/$0.50 per M tokens for prompts up to 100K tokens; prompts over 100K tokens (cache reads and writes included) bill the whole request at $0.50/$2.50. 1M-token context window, 128K max output tokens, adaptive thinking on by default, prompt caching (read $0.01/M, 5-minute write $0.125/M) and web search.

186/929credits

input / output · per 1M tokens

Lowest-cost current Claude model

1M token context window

128K max output tokens

Adaptive thinking on by default (effort default: medium)

Prompt caching (read 10% / 5-min write 125% of input price)

Long-context tier: prompts over 100K tokens bill the whole request at 5x

Web search tool support

Vision and tool use

Streaming support

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Model Specifications

Context Window

tokens

Max Output

128K

tokens

Training Cutoff

Not published

Compatible SDK

Anthropic, OpenAI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	186	$0.12
Output Tokens	929	$0.62
Cached Tokens	18.58	$0.01

* 1,500 credits ≈ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-haiku-5-5",
  "messages": [
    {
      "role": "system",
      "content": "Classify the ticket into exactly one of: billing, account, bug, feature_request, other. Reply with the label only."
    },
    {
      "role": "user",
      "content": "I was charged twice for my October subscription. Can you refund one of them?"
    }
  ],
  "max_tokens": 2000
}'

Parameters

Parameter	Type	Required	Default	Description
`messages`	array	Yes	-	Array of message objects (OpenAI format)
`max_tokens`	integer	No	4096	Maximum tokens in response, thinking included (up to 128000)
`stream`	boolean	No	false	Enable Server-Sent Events streaming

Examples

Ticket Routing

Classify support tickets into queues at Haiku-tier cost

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-haiku-5-5",
  "messages": [
    {
      "role": "system",
      "content": "Classify the ticket into exactly one of: billing, account, bug, feature_request, other. Reply with the label only."
    },
    {
      "role": "user",
      "content": "I was charged twice for my October subscription. Can you refund one of them?"
    }
  ],
  "max_tokens": 2000
}'

Structured Extraction

Pull fields out of free-form text as JSON

curl -X POST "https://api.core.today/llm/anthropic/v1/messages" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "claude-haiku-5-5",
  "messages": [
    {
      "role": "system",
      "content": "Extract company, amount, currency and due_date from the invoice text. Return JSON only."
    },
    {
      "role": "user",
      "content": "Invoice from Acme Corp. Total due: 1,250,000 KRW by November 30, 2026."
    }
  ],
  "max_tokens": 2000
}'

Tips & Best Practices

1Keep prompts at or under 100K tokens (cache reads and writes count) — above that the whole request, output included, bills at 5x

2Thinking is on by default and counts against max_tokens; set effort to low for simple classification

3Prompt caching: read $0.01/M (10%), 5-minute write $0.125/M — cache large repeated contexts

4Web search costs about 18.6 credits per request ($10 per 1,000 searches) on top of token usage

5Non-default `temperature`, `top_p`, `top_k`, `budget_tokens` and assistant prefill return 400 — omit them (the console strips `temperature` automatically)

6US-only inference (inference_geo: us) bills token charges at 1.1x, including the over-100K tier

7Batch API is not available through the gateway