stealthmodels.

MODEL FIELD GUIDE

Claude Haiku 5.5

Fast, low-cost Claude with adaptive reasoning and a million-token context. Prompt-length pricing makes short, high-volume work especially inexpensive.

A good fit for

Summarization, classification, document lookups, compaction, customer support and focused subagent work alongside larger Claude models.

Context window
1,000,000tokens[4]
License
Proprietary hosted service[3]
Model factsArchitecture, context & capabilities
First available
2026-10-07[1]
Developer
Anthropic[1]
Origin
United States[2]
Family
Claude 5.5[1]
Context window
1,000,000 tokens[4]
Maximum output
128,000 tokens[4]
Input
text, image[4]
Output
text[4]
API access & pricingAnthropic API · $0.1 input / $0.5 output · per 1M tokens

Anthropic API, USD per 1M tokens: prompts up to 100,000 tokens, input $0.10, output $0.50, cache read $0.01, 5-minute cache write $0.125, 1-hour cache write $0.20; prompts over 100,000 tokens, input $0.50, output $2.50, cache read $0.05, 5-minute cache write $0.625, 1-hour cache write $1.00. Batch input and output are 50% off.

[4]
  • Anthropic APIObserved 2026-10-08
    Input $0.1Output $0.5Cached read $0.01Cached write $0.125Batch input $0.05Batch output $0.25

    per 1M tokens

    Available

    Prompts up to 100,000 input tokens. Over 100,000: $0.50/M input, $2.50/M output, $0.05/M cache reads, $0.625/M 5-minute cache writes and $1/M 1-hour cache writes. Short-prompt 1-hour cache writes cost $0.20/M. Batch input and output are 50% off.

    claude-haiku-5-5[4] [8]
Measurements & sources8 primary references · Speed & serving conditions

StealthMark score

StealthMark measures fluid and visual intelligence of AI models.

General and Visual

General Intelligence

Perspective, anatomy, correct shadows, purposeful detail and physical consistency.

Visual Intelligence

Likeness, anatomy, detail, light, materials, composition and artistic expression.

Judging

Frontier Models blindly judge the AI generation unbiased through an intricate process. Our researchers control for mistakes.

Overall score

Overall combines weighted task scores on a scale from 0 to 100. Repeating a task does not increase its weight. Estimated means the total includes an estimate for one missing scene.

Benchmaxxing

Benchmaxx flags models that score unusually well on the familiar Pelican task compared with their other benchmark results. The percentage measures that imbalance, not the probability of training contamination. Flagged Pelican scores are excluded from Overall. Pelican never counts toward General or Visual.

We keep some prompts private to discourage test-specific optimization.

Scoring categories

Prompt & likeness

Subjects, actions and likeness.

Anatomy & construction

Coherent bodies, joints and machinery.

Space & placement

Perspective, scale and contact.

Light & reflections

Lighting, shadows and reflections.

Purposeful detail

Clear, purposeful small features.

Artistry & character

Composition, expression and drawing skill.

Materials & effects

Surfaces, texture and movement.

Visual integrity

Clean shapes, layers and edges.

BENCHMARK RESULTS

Compare results

This link opens the same results in the same order.

StealthMark benchmark results

Reset benchmark preferences?

Return to the default view, clear comparison selections and restore the advertisement.