Claude Haiku 5.5

Approved Data Classifications

This model is only approved for Open Data. When leveraging NaviGator AI’s suite offerings, please ensure you are selecting models that meet the compliance requirements in accordance with UF’s Data Classifications, grant awards or project specifications, and state and federal law.

Description

Claude Haiku 5.5 is Anthropic’s fastest model, built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It brings a 1-million-token context window and up to 128K-token outputs to the Haiku tier, and supports adaptive thinking steered by the effort parameter. Pricing is tiered by prompt length, so short, high-volume requests stay inexpensive.

Note that Claude Haiku 5.5 uses the same newer tokenizer as Claude 4.7 and later models, so the same text counts as roughly 30% more tokens than it did on Claude Haiku 4.5. Budget accordingly when migrating.

Capabilities

Model	Knowledge Cutoff	Input	Output	Context Length	Cost (per 1 million tokens)
claude-haiku-5.5	Jun 2026	Text, Image, Pdf	Text	1,000,000	$0.11/1M input $0.55/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens
• Maximum output: 128,000 tokens
• Pricing is tiered by prompt length:
  • Prompts up to 100,000 tokens: $0.11 per 1M input / $0.55 per 1M output
  • Prompts over 100,000 tokens: $0.55 per 1M input / $2.75 per 1M output
• Cache reads: $0.011 per 1M tokens (up to 100,000) / $0.055 per 1M tokens (over 100,000)
• Cache writes: $0.1375 per 1M tokens (up to 100,000) / $0.6875 per 1M tokens (over 100,000)

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "claude-haiku-5.5",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI

client = OpenAI(
    api_key="your_api_key",
    base_url="https://api.ai.it.ufl.edu/v1"
)

response = client.chat.completions.create(
    model="claude-haiku-5.5", # model to send to the proxy
    messages = [
        { "role": "system", "content": "You are a helpful assistant." },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
)

print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "claude-haiku-5.5",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

console.log(completion.choices[0].message)

When to use

• Classification and routing — triaging tickets, tagging content, and directing requests at high volume
• Extraction — pulling structured fields out of documents, forms, and free text
• Subagent tasks — fast workers driven by a larger orchestrating model
• Latency-sensitive interfaces — chat widgets and autocomplete where response time matters most
• Cost-sensitive batch work — large jobs where short prompts keep you in the lower pricing tier

tip

Keep prompts under 100,000 tokens to stay in the lower pricing tier. Crossing that threshold raises input and output costs roughly 5x for the whole request. Setting temperature, top_p, or top_k to a non-default value returns a 400 error.

warning

Claude Haiku 5.5 uses a newer tokenizer than Claude Haiku 4.5, and the same text counts as approximately 30% more tokens. Re-measure token usage before migrating cost-sensitive workloads.

---

References

1. Anthropic - Claude Haiku
   https://www.anthropic.com/claude/haiku
2. Claude Platform Docs - Claude Haiku 5.5
   https://platform.claude.com/docs/en/models/haiku-5-5/overview
3. Claude Platform Docs - What's new in Claude Haiku 5.5
   https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5
4. Claude Platform Docs - Pricing
   https://platform.claude.com/docs/en/about-claude/pricing