Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Tempr Gateway logo

Model details

Claude Haiku 4.5 (latest)

Claude Haiku 4.5 is Anthropic's lightest-weight current member of the Claude family, positioned in the official comparison table as the "Fastest" latency tier alongside higher-priced siblings like Sonnet the listed price, Opus 5.5, and Fable 5.1. It ships with an "Extended" thinking configuration that enables deeper reasoning behavior on demand, while keeping response times minimal for high-throughput scenarios such as real-time assistants, large-scale classification, and embedded agentic workflows where the per-token economics of larger Claude tiers would be impractical.

In practice, Haiku 4.5 is intended for teams who need Claude-quality reasoning at the lowest cost and latency in the lineup, making it well suited for tool-calling pipelines, retrieval-heavy applications, and latency-sensitive customer-facing features. Its placement beneath the Sonnet, Opus, and Fable tiers in the comparison table signals a deliberate trade-off in favor of speed and affordability over the larger context window and higher output ceilings of the more capable Claude models.

Tempr Gatewayanthropic/claude-haiku-4-5claude-haiku

Quick Info

Powered by
Provider
Tempr Gateway
Model key
anthropic/claude-haiku-4-5
Release date
Oct 15, 2025
Last updated
Oct 15, 2025
Knowledge cutoff
2025-02-28
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$1.00
Output token cost
$5.00

Limits

Output tokens
64,000 tokens
Context window
200,000 tokens

Transparent token rates

Compare Claude Haiku 4.5 (latest) pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Claude Haiku 4.5 (latest)

No articles yet. Fetch the latest news to show it here.

Videos about Claude Haiku 4.5 (latest)

More models around Claude Haiku 4.5 (latest)