Claude Haiku 4.5 by FreeModel | AI model information

$10 off the fastest Kimi K3 and GLM 5.3$10 off the fastest Kimi K3 and GLM 5.3

Model details

Claude Haiku 4.5

Anthropic positions Claude Haiku 4.5 as the fastest and most efficient entry in its Claude lineup, designed to deliver near-frontier reasoning at substantially lower latency than larger family members. It is intended for real-time assistants, high-volume pipelines, sub-agent orchestration, and parallelized execution where responsiveness matters as much as raw capability. Extended thinking has been brought to the Haiku tier for the first time, giving developers controllable reasoning depth with summarized or interleaved thought output, which is unusual for a model in this speed class.

On coding workloads Claude Haiku 4.5 reaches 73 percent on SWE-bench Verified, placing it among the strongest coding models available while still behaving like a lightweight, low-latency option. It supports tool-assisted workflows including coding, bash, web search, and computer-use tools, making it suitable as a worker model inside larger agentic systems. Practically it fits scenarios such as customer-facing chat, batch document or PDF analysis, background agents, and on-demand code assistance where the trade-off between cost, speed, and near-frontier quality is more important than maximum single-stream depth.

FreeModelclaude-haiku-4-5-20251001claude-haiku

Open provider page Provider docs

Quick Info

Provider: FreeModel
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

FreeModel

CoverageBenchmark

BenchLM's tracker entry for Claude Haiku 4.5, dated as of September 4, 2026, records the model as released on October 15, 2025 with a 200K context window and proprietary, non-reasoning categorization. API pricing is listed at $1 per million input tokens, $5 per million output tokens, with cached input at $0.10 and a ba The aggregator assigns Claude Haiku 4.5 a composite capability score of 52.7 out of 100, ranking it 112th of 232 tracked models, with its strongest eligible category being Knowledge at a 36th percentile (117th rank). Within tracked benchmarks it ranks 143 of 151 in Agentic and 173 of 183 in Coding. Independent runtime

FreeModel

CoverageBenchmark

OpenRouter's model page for Claude Haiku 4.5 confirms the October 15, 2025 release date and Anthropic's positioning of Haiku 4.5 as its fastest, most efficient model, delivering near-frontier intelligence at lower cost and latency. It matches Claude Sonnet 4's performance on reasoning, coding, and computer-use tasks, a The page lists a 200K context window with $1/$5 per 1M token pricing for input and output, and notes a 73% SWE-bench Verified score. Modalities supported are text and images in with text out. Routing to Azure, Amazon Bedrock, Google Vertex, and Anthropic hosts is documented, though per the instructions this gateway/pro