Claude Haiku 4.5

claude-haiku-4-5

Run Claude Haiku 4.5 in a hosted Python Task with structured output, web search, extended thinking, file inputs and MCP connectors.

Anthropic's fastest model with near-frontier intelligence. Matches Sonnet 4's performance on coding, computer use, and agent tasks while being optimized for speed and cost-efficiency.

What Claude Haiku 4.5 supports in qbash

Structured outputReplies as JSON that matches a schema you pass.
MCP connectorsCalls tools on MCP connectors during a request.
Web searchSearches the web while it answers.
Extended thinkingReasons through a problem before it replies.
Image inputReads WEBP, PNG, JPEG and GIF images.
Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more 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 Haiku 4.5 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: 64,000tokens
Temperature: 0 to 1default 0.7

Structured output with Claude Haiku 4.5 in a Python Task

qbash.ai.raw calls Claude Haiku 4.5 from a Task. Pass a JSON Schema as output_schema and the reply comes back as a Python dict that matches it, ready to route to a connector.

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

triage = qbash.ai.raw(
    f"Summarize this support ticket and rate its urgency:\n\n{ticket}",
    model="claude-haiku-4-5",
    output_schema={
        "type": "object",
        "properties": {
            "summary": {"type": "string"},
            "urgency": {"type": "string", "enum": ["low", "medium", "high"]},
        },
        "required": ["summary", "urgency"],
    },
)

# triage is a dict, e.g. {"summary": "...", "urgency": "high"}
if triage["urgency"] == "high":
    qbash.integrations.slack.create_message(
        channel="#support",
        text=triage["summary"],
    )

qbash.output(triage)

Structured output in Tasks

Connect Claude Haiku 4.5 to MCP servers

In qbash chat and a Task's inline prompts, you can attach MCP connectors to Claude Haiku 4.5. It calls their tools during the request, for example to read a Postgres table or post to a Slack channel.

This is MCP on the model side. Adding MCP servers to Claude Code or Claude Desktop is a separate setup, and qbash can publish your Tasks as an MCP server for those clients as well.

Browse connectors Connect a client

Use Claude Haiku 4.5 with web search

Turn on Web Search in an inline prompt's model bar and Claude Haiku 4.5 searches the web while it answers. Searches are billed at $10.00 per 1,000.

Provider web tools

Extended thinking with Claude Haiku 4.5

Turn on Thinking in the same Settings popover to have Claude Haiku 4.5 reason through a problem before it replies.

Claude Haiku 4.5 pricing

Input	$1.00 per 1M tokens
Output	$5.00 per 1M tokens
Cache read	$0.10 per 1M tokens
Cache write, 5 minutes	$1.25 per 1M tokens
Cache write, 1 hour	$2.00 per 1M tokens
Web search	$10.00 per 1K searches

Standard rates in USD.

Supported file formats

Images

WEBP up to 5 MB
PNG up to 5 MB
JPEG up to 5 MB
GIF up to 5 MB

Documents

PDF
TEXT
DOC
XLS
RTF
DOCX
XLSX
PPTX
PPT
ODT
ODP
ODS