claude-haiku-4.5
Use claude-haiku-4.5 through KeepBal. POST /v1/messages. $1.25 input / $6.25 output per 1M tokens.
curl
curl https://keepbal.com/v1/messages -H 'Authorization: Bearer YOUR_KEEPBAL_KEY' -H 'Content-Type: application/json' -d '{"model":"claude-haiku-4.5","messages":[{"role":"user","content":"Summarize this research."}],"max_tokens":256}'OpenAI SDK
import os
from openai import OpenAI
client = OpenAI(api_key=os.environ["KEEPBAL_API_KEY"], base_url="https://keepbal.com/v1")
# Messages uses its native request format through the SDK HTTP client.
response = client.post("/messages", body={"model":"claude-haiku-4.5","messages":[{"role":"user","content":"Summarize this research."}],"max_tokens":256}, cast_to=dict)
print(response)Pair with tools
Search for source material, inspect and run a tool, then pass the results to a model for summarization or analysis. Browse tools
| Tool | What it returns | Price |
|---|---|---|
| Chatgpt Ask | Get ChatGPT's consumer-app answer to a prompt, with cited sources, in a chosen country. | Provider cost + 35%, quoted by inspect before you run. Quotes are estimates; inspect the spending cap requirements. |
| Copilot Ask | Get Copilot's consumer-app answer to a prompt, with cited sources, in a chosen country. | Provider cost + 35%, quoted by inspect before you run. Quotes are estimates; inspect the spending cap requirements. |
| Gemini Ask | Get Gemini's consumer-app answer to a prompt, with cited sources, in a chosen country. | Provider cost + 35%, quoted by inspect before you run. Quotes are estimates; inspect the spending cap requirements. |
FAQ
Which endpoint should I use?
POST /v1/messages with the exact model ID claude-haiku-4.5.
How is usage priced?
$1.25 input / $6.25 output per 1M tokens. Billing uses returned token usage.