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

Model details

Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic's lightweight, speed-focused entry in the Haiku family, designed to deliver near-flagship behavior at lower cost and latency for production workloads. Officially announced on October 15, 2025, it is positioned as a lightweight counterpart to the company's most capable model, aiming to match prior Sonnet 4 levels of performance on coding, computer use, and agent-style tasks while remaining economical enough for high-volume deployment. The model's emphasis on speed and efficiency makes it attractive for chat assistants, IDE integrations, and any workflow that needs quick, capable responses without invoking a larger model.

For coding applications, Anthropic reports that Claude Haiku 4.5 scores 73.3% on SWE-bench Verified, a result the company highlights as putting it among the world's best coding models for its tier and giving it strong real-world software engineering capability. It is available both through the consumer-facing Claude.ai experience and to developers via the Anthropic API platform, with the same model also surfaced through Claude Code, Amazon Bedrock, Google Cloud Vertex AI, and Microsoft Foundry. Independent coverage has framed the release as a faster, lower-cost option relative to larger Claude variants, reinforcing its role as the practical choice when teams need strong reasoning and coding performance at a fraction of the compute footprint.

DevPass (LLM Gateway)claude-haiku-4-5-20251001claude-haiku

Quick Info

Powered by
Provider
DevPass (LLM Gateway)
Model key
claude-haiku-4-5-20251001
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 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

DevPass (LLM Gateway)

CoverageBenchmark

The n8n AI benchmark listing names Claude Haiku 4.5 explicitly as Anthropic's fastest and most efficient model, delivering near-frontier intelligence at lower cost and latency than larger Claude variants while matching Claude Sonnet 4's performance on reasoning, coding, and computer-use tasks. It confirms a 200,000-tok According to n8n's benchmark page, Claude Haiku 4.5 introduces extended thinking to the Haiku line, supporting controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows including coding, bash, web search, and computer-use tools. The model scores 73% on SWE-bench Verified, placi

Videos about Claude Haiku 4.5

More models around Claude Haiku 4.5