Skip to main content
All models

Claude 3.5 Haiku

OpenRouterOpenRouter docs

anthropic/claude-3.5-haiku

Run Claude 3.5 Haiku in a hosted Python Task with file inputs.

Fast and efficient model from Anthropic's Claude 3.5 series via OpenRouter. Designed for quick, straightforward tasks.

Deprecated model

This model is deprecated and not recommended for new projects.

What Claude 3.5 Haiku supports in qbash

  • Document inputReads TEXT, XLS, RTF and XLSX files.
  • Prompt cachingRepeated input is billed at the cached rate.

What is qbash?

qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like Claude 3.5 Haiku only at the ones that need judgment, with integrations, memory and files available in the same script.

A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.

How Tasks work

Specifications

Context window
200Ktokens
Max output
8,192tokens
Temperature
0 to 2default 1

Use Claude 3.5 Haiku in a Python Task

qbash.ai.raw calls Claude 3.5 Haiku from a Task and returns its reply as a string.

main.py
notes = qbash.inputs.get("notes")

summary = qbash.ai.raw(
    f"Summarize these meeting notes in five bullets:\n\n{notes}",
    model="anthropic/claude-3.5-haiku",
    system="You are a concise analyst.",
)

qbash.output({"summary": summary})
Model calls in Tasks

Claude 3.5 Haiku pricing

Input$0.80 per 1M tokens
Output$4.00 per 1M tokens
Cached input$0.08 per 1M tokens
Cache write$1.00 per 1M tokens
Web search$10.00 per 1K searches

Standard rates in USD.

Supported file formats

Documents

  • TEXT
  • XLS
  • RTF
  • XLSX

Automate Claude 3.5 Haiku with qbash