VENICE ATLAS · MODEL DOSSIER · CLAUDE HAIKU 5.5

Model overview

Claude Haiku 5.5

Name: Claude Haiku 5.5
Brand: venice.ai
Price: 0.1000 USD
Availability: InStock

Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.

claude-haiku-5-5 · venice.ai

Text · Venice catalog$0.10 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.10 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks36Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Agents#2133.88 rating Coding#939.22 rating Vision#3230.29 rating General intelligence#1549.80 rating Healthcare#1431.95 rating Multimodal#2631.31 rating Productivity#134.45 rating Reasoning#2147.22 rating Science#200.71 rating

Agents4 results

AA-Briefcase v1.1aa-briefcase-1.1 · agents

52.6%

ReportedOct 2026

OfficeQAofficeqa · agents

73.5%

ReportedOct 2026

OfficeQA Proofficeqa-pro · agents

60.3%

ReportedOct 2026

Program Benchprogram-bench · agents

82.0%

ReportedOct 2026

Biology8 results

Biomedical image analysisbiomedical-image-analysis · biology

43.5%

ReportedOct 2026

LatchBio SpatialBench Verifiedlatchbio-spatialbench-verified · biology

67.7%

ReportedOct 2026

Medicinal Chemistry (ADME)medicinal-chemistry-adme · biology

58.0%

ReportedOct 2026

Morphology-to-molecule matchingmorphology-to-molecule-matching · biology

25.4%

ReportedOct 2026

Protein Design — Library Rankingprotein-design-library-ranking · biology

45.3%

ReportedOct 2026

Protein Design — Sequence Generationprotein-design-sequence-generation · biology

33.1%

ReportedOct 2026

Protocols Troubleshootingprotocols-troubleshooting · biology

58.0%

ReportedOct 2026

Protocols Understanding (V2)protocols-understanding-v2 · biology

64.1%

ReportedOct 2026

Coding3 results

BenchCADbenchcad · code

67.0%

ReportedOct 2026

BenchCAD (with Python tool)benchcad-with-python-tool · code

87.0%

ReportedOct 2026

FrontierSWE V2frontierswe-v2 · code

43.8%

ReportedOct 2026

General intelligence2 results

GDPval-AA 2.1gdpval-aa-2.1 · general

54.0%

ReportedOct 2026

Global-MMLUglobal-mmlu · general

87.8%

ReportedOct 2026

Healthcare4 results

HealthBenchhealthbench · healthcare

61.6%

ReportedOct 2026

HealthBench Professionalhealthbench-professional · healthcare

64.8%

ReportedOct 2026

HealthBench Professional (raw)healthbench-professional-raw · healthcare

71.0%

ReportedOct 2026

PhysicianBenchphysicianbench · healthcare

43.0%

ReportedOct 2026

Language1 result

MILUmilu · language

87.6%

ReportedOct 2026

Multimodal2 results

OSWorld 2.1 (partial)osworld-2.1-partial · multimodal

72.4%

ReportedOct 2026

OSWorld 2.1 (strict)osworld-2.1-strict · multimodal

37.1%

ReportedOct 2026

Reasoning6 results

FrontierCode 1.1frontiercode-1.1 · reasoning

46.4%

ReportedOct 2026

FrontierCode 1.1 (Extended)frontiercode-1.1-extended · reasoning

58.4%

ReportedOct 2026

Humanity's Last Exam (no tools, text-only)humanity's-last-exam-(no-tools,-text-only) · reasoning

45.9%

ReportedOct 2026

Humanity's Last Exam (with tools)humanity's-last-exam-(with-tools) · reasoning

57.4%

ReportedOct 2026

SWE-bench Multilingualswe-bench-multilingual · reasoning

83.7%

ReportedOct 2026

SWE-Bench Multimodalswe-bench-multimodal · reasoning

30.7%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.10
Output price per 1M tokens: $0.50
Cache read price per 1M tokens: $0.0100
Cache write price per 1M tokens: $0.13
Blended price per 1M tokens (50/50): $0.30

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionWeb search

Endpoint metadata

Privacy: anonymized
Quantization: not-available
Maximum completion tokens: 128K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

All capabilities

Max Images: 10
Quantization: not-available
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: No
Default Reasoning Effort: medium
Reasoning Effort Options: none, low, medium, high, xhigh, max
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from anthropic

claude-sonnet-5-5Claude Sonnet 5.5$2.00 input per 1M tokens ↗claude-opus-5-5Claude Opus 5.5$4.00 input per 1M tokens ↗claude-fable-5-1Claude Fable 5.1$10.00 input per 1M tokens ↗