Claude Haiku 4.5 API

Claude Haiku 4.5 is Anthropic's small model, released in October 2025. In Jantaris it has a 200,000-token context window and up to 64K output tokens. At launch Anthropic said it matches the coding level of Claude Sonnet 4 at about a third of the cost and more than twice the speed, and that it beats Sonnet 4 at some computer-use tasks. It is the Claude to pick when response time and volume matter more than peak reasoning.

Best for

• Customer support bots and chat assistants that must reply quickly
• Sub-agents that a larger model sends small tasks to in parallel
• Classification, tagging and data extraction at high volume
• Quick pair programming and prototyping in Claude Code

How to call it

Use the OpenAI SDK with the Jantaris endpoint:

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="claude-haiku-4.5",
    messages=[{"role": "user", "content": "Tag this ticket: billing, bug or feature request?"}],
)
print(resp.choices[0].message.content)

It also works with the Anthropic SDK and Claude Code through /v1/messages, see the Claude Code guide.

FAQ

How much is Claude Haiku 4.5 per million tokens?

$1.35 / $6.75 per 1M tokens in Jantaris. That makes it the lowest-priced Claude in the catalog, which matters when you process thousands of short requests a day.

Is a 200K context window enough?

For chat, support and extraction, yes: 200K tokens holds a long conversation plus a sizable knowledge base excerpt. For whole repositories or big document sets, use a 1M-token model such as Claude Sonnet 5.

Can Haiku 4.5 work as a sub-agent next to a bigger Claude?

Yes, Anthropic suggests exactly that setup: a larger model plans the work and several Haiku 4.5 instances handle the subtasks. In Jantaris all of them run on the same key and balance, so you see the full cost of the workflow in one place.

How to call Claude Haiku 4.5 via API

from openai import OpenAI

client = OpenAI(base_url="https://jantaris.com/v1", api_key="sk-jt-...")
resp = client.chat.completions.create(
    model="claude-haiku-4.5",
    messages=[{"role": "user", "content": "Write a haiku about Baltic amber."}],
)
print(resp.choices[0].message.content)

curl https://jantaris.com/v1/chat/completions \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-haiku-4.5", "messages": [{"role": "user", "content": "Write a haiku about Baltic amber."}]}'

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://jantaris.com/v1", apiKey: process.env.JANTARIS_API_KEY });
const resp = await client.chat.completions.create({
  model: "claude-haiku-4.5",
  messages: [{ role: "user", content: "Write a haiku about Baltic amber." }],
});
console.log(resp.choices[0].message.content);

export ANTHROPIC_BASE_URL=https://jantaris.com
export ANTHROPIC_AUTH_TOKEN=sk-jt-...
export ANTHROPIC_MODEL=claude-haiku-4.5
claude