Chat & Reasoning Model · Anthropic

Claude Haiku 4.5

Claude Haiku 4.5 is a previous-generation Haiku built for real-time chat, high-volume tasks, and latency-sensitive work, with a 200K-token context window. It was succeeded by Claude Haiku 5.5 on October 7, 2026; Teamday agents configured with Haiku 4.5 now run on Claude Haiku 5.5.

At a glance (verified 2026-10-07)

Vendor
Anthropic
Type
Chat & Reasoning Model
Pricing
Base: $1 in / $0.10 cache hits / $5 out per 1M tokens. Cache writes: $1.25 5m / $2 1h.

Best for

Real-time chatHigh-volume tasksLatency-sensitive workCost control

How to use Claude Haiku 4.5 in Teamday

Claude Haiku 4.5 is no longer in Teamday's chat model picker — pick Claude Haiku 5.5, its successor on the Claude Code harness. Existing agents set to Haiku 4.5 are moved to Haiku 5.5 automatically.

Frequently asked questions

How much does Claude Haiku 4.5 cost?

Base pricing is $1 per 1M input tokens, $0.10 for cache hits, and $5 per 1M output tokens; cache writes cost $1.25 (5-minute) or $2 (1-hour). Its successor, Claude Haiku 5.5, costs $0.10 in / $0.50 out on prompts up to 100K tokens.

What is Claude Haiku 4.5 best for?

It was pitched for real-time chat, high-volume tasks, and anything latency-sensitive. Claude Haiku 5.5 now covers the same work with a larger context window.

Is Claude Haiku 4.5 available in Teamday?

It has been replaced by Claude Haiku 5.5 in Teamday's chat model picker. Agents and chats previously set to Haiku 4.5 run on Claude Haiku 5.5 automatically.

Related

Claude Haiku 4.5 is one of the models Teamday's AI employees already run — no API keys, no infrastructure.

Hire your first AI employee →