llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsClaude Haiku 4.5

Anthropic model product

Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic's fastest, most cost-efficient model, matching Sonnet 4's performance on coding, computer use, and agent tasks. It offers similar performance to Sonnet 4 at one-third the cost and more than twice the speed, making it ideal for high-volume, latency-sensitive applications and multi-agent orchestration.

Updated Aug 10, 2026. Default version: Claude Haiku 4.5

Compare
LLMBoard scoreN/ANot scored
CoverageN/ANo published score
Context window200KTokens
Official input price$1Anthropic API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Claude Haiku 4.5
Released
Oct 15, 2025
Knowledge cutoff
Feb 1, 2025
Parameters
N/A
Context window
200K
Max output
64K
Inputs
image, pdf, text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

No capability profile

No published version under this unique model currently has enough benchmark coverage to calculate a score.

Benchmark results

Published benchmark records for the scored version currently unavailable.

No benchmark rows

No published benchmark result is linked to the scored version.

Arena results

Preference and agent-evaluation signals from published Arena datasets.

93 rows
Columns

Show columns

documentoverall301423.030,937N/AJul 30, 2026
document style controloverall361422.230,937N/AJul 30, 2026
text factualityjapanese371380.8490N/AAug 6, 2026
text factualitykorean371358.1765N/AAug 6, 2026
text factualitygerman391379.0837N/AAug 6, 2026
text factualityspanish421433.81,923N/AAug 6, 2026
text factualitypolish531362.11,642N/AAug 6, 2026
text factualityexpert631464.16,529N/AAug 6, 2026
text factualityfrench651426.52,133N/AAug 6, 2026
text factualityindustry mathematical661426.93,782N/AAug 6, 2026
text factualitycoding701489.322,138N/AAug 6, 2026
textexpert721442.99,203N/AAug 6, 2026
text factualitylonger query761448.432,732N/AAug 6, 2026
textcoding791450.828,992N/AAug 6, 2026
textinstruction following791413.334,915N/AAug 6, 2026
textlonger query791427.139,621N/AAug 6, 2026
text style controlspanish791428.53,047N/AAug 6, 2026
webdevwebdev-react791322.913,205N/AAug 6, 2026
text factualityinstruction following811426.827,357N/AAug 6, 2026
text factualitymath811407.84,031N/AAug 6, 2026
text factualitychinese821445.14,016N/AAug 6, 2026
text factualityhard prompts english861464.125,974N/AAug 6, 2026
webdevoverall861324.924,666N/AAug 6, 2026
webdevwebdev861324.924,666N/AAug 6, 2026
text style controlcoding881479.228,992N/AAug 6, 2026
text style controlexpert881454.09,203N/AAug 6, 2026
webdevwebdev-html881314.49,888N/AAug 6, 2026
text factualityrussian891413.77,320N/AAug 6, 2026
textspanish901418.03,047N/AAug 6, 2026
text factualityindustry software and it services901467.235,812N/AAug 6, 2026
text factualityindustry legal and government911430.65,473N/AAug 6, 2026
text factualitymulti turn911431.114,140N/AAug 6, 2026
text factualityindustry business and management and financial operations921428.415,612N/AAug 6, 2026
text factualityindustry entertainment and sports and media921397.017,059N/AAug 6, 2026
text factualityindustry writing and literature and language931406.419,591N/AAug 6, 2026
text factualitycreative writing941395.512,395N/AAug 6, 2026
text style controllonger query941436.939,621N/AAug 6, 2026
text factualityindustry medicine and healthcare951433.35,029N/AAug 6, 2026
texthard prompts english971434.533,676N/AAug 6, 2026
text style controlhard prompts english971454.733,676N/AAug 6, 2026
text style controlindustry software and it services971462.843,143N/AAug 6, 2026
textindustry mathematical981424.75,693N/AAug 6, 2026
text style controlindustry mathematical1001430.55,693N/AAug 6, 2026
text style controlinstruction following1001415.334,915N/AAug 6, 2026
textindustry software and it services1041436.443,143N/AAug 6, 2026
text style controlmulti turn1041424.320,438N/AAug 6, 2026
text factualityenglish1051433.249,505N/AAug 6, 2026
text factualityhard prompts1051445.364,583N/AAug 6, 2026
text style controlindustry writing and literature and language1061399.226,460N/AAug 6, 2026
text style controlkorean1061359.41,725N/AAug 6, 2026
text style controlenglish1071432.053,815N/AAug 6, 2026
text style controlindustry business and management and financial operations1071416.822,224N/AAug 6, 2026
text style controljapanese1071353.41,078N/AAug 6, 2026
text style controlgerman1081402.71,901N/AAug 6, 2026
text factualityindustry life and physical and social science1091433.812,747N/AAug 6, 2026
text style controlfrench1101427.63,042N/AAug 6, 2026
text style controlhard prompts1101440.068,830N/AAug 6, 2026
text style controlindustry entertainment and sports and media1101388.723,084N/AAug 6, 2026
text style controlcreative writing1121389.017,811N/AAug 6, 2026
texthard prompts1131418.268,830N/AAug 6, 2026
textjapanese1131329.91,078N/AAug 6, 2026
text factualityoverall1151416.4108,067N/AAug 6, 2026
text factualityexclude ties1161405.780,302N/AAug 6, 2026
textmulti turn1171407.120,438N/AAug 6, 2026
textindustry writing and literature and language1181385.526,460N/AAug 6, 2026
textcreative writing1191371.717,811N/AAug 6, 2026
textindustry business and management and financial operations1211396.222,224N/AAug 6, 2026
textfrench1221407.43,042N/AAug 6, 2026
textindustry entertainment and sports and media1221368.723,084N/AAug 6, 2026
text style controloverall1221412.4114,721N/AAug 6, 2026
text style controlindustry life and physical and social science1221430.018,442N/AAug 6, 2026
text factualitynon english1231395.956,868N/AAug 6, 2026
text style controlexclude ties1241399.785,411N/AAug 6, 2026
textenglish1251413.953,815N/AAug 6, 2026
textkorean1251337.71,725N/AAug 6, 2026
text style controlindustry legal and government1281414.88,421N/AAug 6, 2026
textgerman1291374.01,901N/AAug 6, 2026
text style controlchinese1291437.05,864N/AAug 6, 2026
text style controlrussian1291398.410,957N/AAug 6, 2026
text style controlnon english1331389.460,848N/AAug 6, 2026
text style controlindustry medicine and healthcare1361425.17,529N/AAug 6, 2026
textindustry legal and government1371397.78,421N/AAug 6, 2026
textchinese1381422.75,864N/AAug 6, 2026
textexclude ties1381372.685,411N/AAug 6, 2026
text style controlpolish1381371.52,904N/AAug 6, 2026
textoverall1391393.8114,721N/AAug 6, 2026
textrussian1391377.310,957N/AAug 6, 2026
text style controlmath1391398.46,534N/AAug 6, 2026
textindustry life and physical and social science1401402.818,442N/AAug 6, 2026
textindustry medicine and healthcare1411390.87,529N/AAug 6, 2026
textmath1431392.96,534N/AAug 6, 2026
textnon english1451370.760,848N/AAug 6, 2026
textpolish1541342.82,904N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$1 input, $5 output per 1M
Official provider
Anthropic
Lowest third-party
From $0.14 input, $0.71 output per 1M via QiHang
Tracked offerings
11
11 rows
Columns

Show columns

QiHangclaude-haiku-4-5-20251001global$0.14$0.71200KAug 7, 2026
Jiekou.AIclaude-haiku-4-5-20251001global$0.90$4.520KAug 7, 2026
NanoGPTclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
DaoXEclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
LLM Gatewayclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
302.AIclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
Heliconeclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
Abacusclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
FreeModelclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
Anthropicclaude-haiku-4-5-20251001global$1$5200KAug 7, 2026
UnoRouterclaude-haiku-4-5-20251001global$1.2$6200KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Claude Haiku 4.5 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Claude Haiku 4.5Oct 15, 2025N/AN/A200K64KNoProprietary

What is Claude Haiku 4.5?

A concise description based on the published model registry.

Claude Haiku 4.5 is Anthropic's fastest, most cost-efficient model, matching Sonnet 4's performance on coding, computer use, and agent tasks. It offers similar performance to Sonnet 4 at one-third the cost and more than twice the speed, making it ideal for high-volume, latency-sensitive applications and multi-agent orchestration.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Models similar to Claude Haiku 4.5

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#129
AN

Claude Haiku 3

Anthropic

34.1 LLMBoard

DetailsCompare
#114
AN

Claude Sonnet 3

Anthropic

40.0 LLMBoard

DetailsCompare
#110
AN

Claude Haiku 3.5

Anthropic

41.2 LLMBoard

DetailsCompare
#55
AN

Claude Opus 3

Anthropic

58.8 LLMBoard

DetailsCompare
#41
AN

Claude Sonnet 3.7

Anthropic

63.6 LLMBoard

DetailsCompare
#33
AN

Claude Opus 4.6

Anthropic

69.2 LLMBoard

DetailsCompare

FAQ

Common questions about Claude Haiku 4.5.

When was Claude Haiku 4.5 released?

Claude Haiku 4.5's default version was released on Oct 15, 2025.

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5's official API price is $1 per million input tokens and $5 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.14 input and $0.71 output via QiHang.

Who created Claude Haiku 4.5?

Claude Haiku 4.5 is published under Anthropic in the model registry.

What is the context window for Claude Haiku 4.5?

The default version has a 200K token context window.

Is Claude Haiku 4.5 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Claude Haiku 4.5?

11 published provider offerings are linked to the default version.

What models should I compare Claude Haiku 4.5 with?

No nearby ranked alternatives are currently available.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai