Minaco

Claude Haiku 5.5

Haiku 5.5 targets low-latency tasks such as classification, extraction and routing.

When to try it.

Try clearly specified transformations or sorting work with a stable output format and examples.

What to weigh

A smaller task scope makes quality easier to assess. Escalate ambiguous decisions to a more capable model when your checks expose gaps.

A first task

Classify these issues using the provided labels. Include the evidence for each label and mark uncertain cases.

This is a suggested evaluation task. Check the result against your own requirements; it is not a benchmark or a guarantee of performance.

Know the rate.

Currently published for Claude Code. Rates below are Minaco Credits per one million tokens.

Claude Haiku 5.5 · prompt ≤ 100,000

Input
190
Cached input
19
Output
950

Cache writes: 237.5 (5 min) / 380 (1 hour) Credits per million tokens.

Claude Haiku 5.5 · prompt > 100,000

Input
950
Cached input
95
Output
4,750

Cache writes: 1,187.5 (5 min) / 1,900 (1 hour) Credits per million tokens.

The prompt total includes input, cached reads and cache writes. Its tier applies to the entire request.

Estimate a model call

Example: 10,000 uncached input tokens and 1,000 output tokens cost approximately 2.85 Credits before per-request rounding.

An agent turn may make several model calls. Context, tool results and billable reasoning tokens affect the total; enter cache-write tokens separately when applicable. The prompt total determines the rate for the whole request. This estimate is not a charge cap or a checkout quote. How Credits work.

Exact route: claude-haiku-5-5

Catalog checked 2026-11-17. Model access depends on your plan and current service availability.

Use it in your workspace.

  1. Prepare Claude Code

    Install Minaco on your Apple silicon Mac, connect your account and prepare the native agent in Agent settings.

  2. Choose the exact model

    Select Claude Code and a Minaco-credit account mode. If your plan offers Claude Haiku 5.5, choose it from the model selector. Desktop 0.13.14 or later reads the server’s model catalog.

  3. Give it a bounded task

    Open the project folder, provide the necessary context and review any approvals. Inspect the result and usage before expanding the scope.

When the next stage calls for a different agent, finish the turn and switch in the same conversation. Minaco prepares the visible working context for the next native session; hidden reasoning and credentials do not transfer.

How context handoff works →

Read the source.

Claude model documentation describes the upstream model.

Editorial review: 2026-11-11. Task suggestions and comparisons are Minaco’s guidance, not vendor benchmark results. Minaco is an independent workspace; model API features do not imply that every feature is exposed by the native agent.

Compare nearby choices.

  • Claude Sonnet 5.5 — Sonnet 5.5 is the balanced option in the current Claude family.
  • Claude Opus 5.5 — Opus 5.5 is positioned for agentic coding and knowledge work.
  • Claude Fable 5.2 — Fable 5.2 is the newer Fable model, announced on November 9, 2026, for demanding reasoning and long-horizon work.

Keep the work moving.

Your agents. Your workspace. One place to continue.

Download for Mac