# Claude Haiku 4.5

Anthropic, released 2025-10-15

**Verdict: recommended.** Anthropic's value baseline at $1/$5 per 1M tokens — the fast, low-cost tier rivals benchmark against, with 200K context and 64K output. Best for high-volume latency-sensitive work: classification, extraction, summarization, routing. Reach for Opus 4.8 or Sonnet 5 when deep multi-step reasoning is needed. Last verified 2026-10-19.

## Pricing

- Input: $1 / 1M tokens
- Output: $5 / 1M tokens
- Context: 200K ctx; legacy, Haiku 5.5 is current

## Strengths

- High-volume, latency-sensitive workloads — classification, extraction, routing, summarization, and cheap agent sub-steps at $1/$5 per 1M tokens
- Cost-efficient agent swarms and sub-agents — the budget tier of a Haiku > Sonnet > Opus escalation ladder
- Larger-context budget work — 200K context and up to 64K output, far beyond Haiku 3.5's 8K limit
- Complex multi-file architecture or frontier reasoning — route those to Sonnet 5 or Opus 4.8; Haiku is not a frontier model
- Absolute-cheapest coding value in the lightweight tier — Microsoft's MAI-Code-1-Flash claims a 16-point SWE-Bench Pro lead over Haiku 4.5 inside Copilot

## Sources

- [Anthropic pricing page](https://platform.claude.com/docs/en/about-claude/pricing)
- [Anthropic Pricing](https://www.anthropic.com/pricing)
- [Neomanex — Microsoft's MAI-Code-1-Flash Goes GA on GitHub Copilot (Haiku 4.5 comparison)](https://utility.neomanex.com/news/microsoft-mai-code-1-flash-copilot)

Canonical: https://neomanex.com/models/claude-haiku-4-5