Is Claude Haiku 5.5 available with Zero Data Retention on Elosia?

Claude Haiku 5.5 runs on Elosia's standard backend; ZDR is available on many other models in the catalog.

How much does Claude Haiku 5.5 cost on Elosia?

Claude Haiku 5.5 is billed by usage at $0.09999999999999999 per 1M input tokens and $0.5 per 1M output tokens, within your Elosia plan.

What is Claude Haiku 5.5's context window?

Claude Haiku 5.5 supports a context window of up to 1,000,000 tokens.

Is Claude Haiku 5.5 hosted in the EU?

Yes, Claude Haiku 5.5 is available on Elosia's EU-hosted (EdenAI) backend for enterprise organizations.

When should you choose Claude Haiku 5.5?

Claude Haiku 5.5 is a compact model, best for high-throughput, latency-sensitive or cost-sensitive workloads.

Claude Haiku 5.5

ClaudeCompact

ThinkingTool UseVisionStructured Output

About this model

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...

Performance Tier

Compact

Claude Haiku 5.5 is a compact model from Claude : optimized for speed and affordability.

Small, fast, and affordable. Optimized for speed and low cost, great for high-volume or simple tasks.

Pricing

This model is included in Elosia plans

Affordable

Low cost. Suitable for sustained use and high-volume interactions.

Type	per 1M tokens
Input (prompt)	$0.100
Output (completion)	$0.500
Cache read	$0.010
Cache write	$0.125

Capabilities

Context Length1.0M

Max Output Tokens128K

TokenizerClaude

Inputtext, image, file

Outputtext

Release DateOctober 7, 2026

Benchmarks

General Intelligence

MMLU

Not reported

Mathematics

MATH-500

Not reported

Programming

HumanEval

Not reported

SWE-bench Multilingual

83.7%

Reasoning

Humanity's Last Exam

45.9%

Agentic

SWE-bench Pro

64.8%

Where does Claude Haiku 5.5 stand?

Compare its performance index against every other model.

View the performance leaderboard

Recommended Use Cases

General ChatSummarizationData ExtractionCustomer SupportCoding

Strengths

Built for high-volume, latency-sensitive work such as summarization, classification, routing, extraction and live customer support
Works as a fast subagent for coding and well-defined tasks, including focused edits that apply across many files
Computer use for repetitive tasks such as form filling, data entry and moving information between apps
Adaptive thinking on by default
1M-token context window, 128K output, and text, image and file input; Anthropic's testing reports strong robustness to prompt injection in coding and computer use environments, and it is available with zero data retention

Limitations

Anthropic positions it for narrowly scoped tasks; it is not designed for complex, long-running agentic coding
The system card reports frequent over-refusals in Anthropic's automated behavioral audit, and its cybersecurity safeguards block penetration testing and similar offensive techniques
The system card flags factual hallucinations as a weak point, along with occasionally using a leaked answer without telling the user
Anthropic publishes no GPQA Diamond, SWE-bench Verified, MMMU-Pro or ARC-AGI-2 score for this model