Claude Haiku 4.5
claude-haiku-4.5
claude-haiku-4.5 is available at claude-haiku-4.5. Below: price, specifications and request examples.
Price
| model value | Input, per 1M | Output, per 1M | Cache, per 1M |
|---|---|---|---|
| claude-haiku-4.5 | $0.3716 | $1.8572 | $0.0372 |
Prices per 1M tokens. You pay for what you use.
Specifications
- Context window
- 200,000 tokens
- Max output tokens
- 16,000 tokens
- Image input
- yes
- Reasoning
- no
- Anthropic format (/v1/messages)
- yes
- Data in Russia
- no
Request example
Create a key in the dashboard. Streaming works too: add "stream": true.
curl https://whitelabel-demo.getvibeapi.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-haiku-4.5", "messages": [{"role": "user", "content": "Hello!"}]}'from openai import OpenAI
client = OpenAI(base_url="https://whitelabel-demo.getvibeapi.com/v1", api_key="YOUR_KEY")
reply = client.chat.completions.create(
model="claude-haiku-4.5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)Questions and answers
How much does claude-haiku-4.5 cost?
Input is $0.3716 per 1M tokens, output $1.8572 per 1M. You are charged for the tokens actually used, so a single request costs a fraction of a cent. Your balance and spending are in the dashboard.
What is the context window of claude-haiku-4.5?
Up to 200,000 input tokens and up to 16,000 output tokens.
How do I call claude-haiku-4.5?
Set the base URL to https://whitelabel-demo.getvibeapi.com/v1 and use "claude-haiku-4.5" in the model field of any OpenAI-compatible client. curl and Python examples are on this page.
Is cached input cheaper?
Repeated context is billed at the cache price — $0.0372 per 1M tokens instead of $0.3716.
Does claude-haiku-4.5 understand images?
Yes, images can be sent along with text.
Other models
Start using claude-haiku-4.5 in minutes
Sign up by email, create a key in the dashboard, top up your balance without a contract.