Anthropic: Claude Haiku 5.5 (batch)

Text input File input Image input Text output
Author's Description

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

Key Specifications
Cost
$$$
Context
1M
Released
Oct 07, 2026
Speed
★★★★
Ability
★★★★
Reliability
★★★★★
Supported Parameters

This model supports the following parameters:

Structured Outputs Tool Choice Reasoning Include Reasoning Response Format Stop Tools Max Tokens
Features

This model supports the following features:

Tools Structured Outputs Response Format Reasoning
Performance Summary

Anthropic's Claude Haiku 5.5, released on October 7, 2026, is positioned as a small, fast model optimized for high-volume, cost-sensitive tasks. It performs among the fastest models, ranking in the 76th percentile for speed across benchmarks. The model also offers competitive pricing, placing in the 63rd percentile for cost-effectiveness. Notably, Claude Haiku 5.5 demonstrates exceptional reliability, achieving a perfect 100% success rate across all benchmarks, indicating consistent and usable responses. In terms of specific capabilities, the model exhibits a significant strength in Coding, achieving an outstanding 98.0% accuracy (99th percentile), making it a top performer in this domain. Its Reasoning and Mathematics capabilities are also strong, with 96.0% and 94.0% accuracy respectively, placing it in the upper quartiles. While its Instruction Following accuracy of 71.0% is solid, it represents a relative area for potential improvement compared to its other high-performing categories. Overall, Claude Haiku 5.5 excels in technical domains like coding and complex problem-solving, making it well-suited for its intended applications.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.1
Completion $0.5
Input Cache Read $0.01
Input Cache Write $0.125
Web Search $10000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Anthropic
Anthropic | anthropic/claude-haiku-5.5-20261007 1M $0.1 / 1M tokens $0.5 / 1M tokens
Google
Google | anthropic/claude-haiku-5.5-20261007 1M $0.1 / 1M tokens $0.5 / 1M tokens
Claude Platform on AWS
Claude Platform on AWS | anthropic/claude-haiku-5.5-20261007 1M $0.1 / 1M tokens $0.5 / 1M tokens
Azure
Azure | anthropic/claude-haiku-5.5-20261007 1M $0.1 / 1M tokens $0.5 / 1M tokens
Amazon Bedrock
Amazon Bedrock | anthropic/claude-haiku-5.5-20261007 1M $0.1 / 1M tokens $0.5 / 1M tokens
Google
Google | anthropic/claude-haiku-5.5-20261007 1M $0.11 / 1M tokens $0.55 / 1M tokens
Google
Google | anthropic/claude-haiku-5.5-20261007 1M $0.11 / 1M tokens $0.55 / 1M tokens
Azure
Azure | anthropic/claude-haiku-5.5-20261007 1M $0.11 / 1M tokens $0.55 / 1M tokens
Amazon Bedrock
Amazon Bedrock | anthropic/claude-haiku-5.5-20261007 1M $0.11 / 1M tokens $0.55 / 1M tokens
Amazon Bedrock
Amazon Bedrock | anthropic/claude-haiku-5.5-20261007 1M $0.11 / 1M tokens $0.55 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by anthropic