That's NeuralModel catalog

anthropic

Anthropic: Claude Haiku 4.5 (batch)

anthropic/claude-haiku-4.5:batch

Our take

AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.

OpenRouter's catalog presents anthropic/claude-haiku-4.5:batch as an Anthropic Claude Haiku 4.5 batch variant linked to the claude-4.5-haiku-20251001 canonical model. The listing reports text, image and file inputs with text output, a 200,000-token context window, tool and structured-output controls, and optional reasoning-related parameters. Its catalog description claims speed, efficiency and near-frontier capability. Third-party catalog measurements cover selected design, coding, agentic and intelligence categories, but they do not guarantee workload results.[1]

Strengths

  • Catalog-reported text, image and file inputs with text output.[1]
  • A listed 200,000-token context window for long inputs.[1]
  • Listed controls include tools, structured output, sampling options and non-mandatory reasoning parameters.[1]

Limitations

  • Only OpenRouter catalog evidence was supplied; an independent model card was not available in this source pack.[1]
  • Text is the only listed output modality; image and file support applies to inputs.[1]
  • Batch behavior, knowledge cutoff and expiration are unspecified, and limited third-party measurements require validation on representative workloads.[1]

Where to use it

  • Consider for bulk or deferred text-processing pipelines if the provider's batch semantics fit the application.[1]
  • Consider for document, image or file-to-text workflows that need long-context input.[1]
  • Consider for tool-assisted or structured-output applications after representative testing.[1]

Sources

  1. [1] OpenRouter catalog · Anthropic: Claude Haiku 4.5 (batch)Sources checked: Nov 13, 2026

About this model

Description below is the original text supplied by OpenRouter, shown in the source language.

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

Specifications

Model ID
anthropic/claude-haiku-4.5:batch
Canonical ID
anthropic/claude-4.5-haiku-20251001
Creator
anthropic
Added to OpenRouter
15.10.2025
Context length
200,000
Modality
text+image+file->text
Input modalities
text, image, file
Output modalities
text
Token pricing
USD per 1M tokens: in $0.500 / out $2.5
Knowledge cutoff
—
Expiration date
—

Tasks and capabilities

A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.

TaskGradeSource-declared capability
General qualityCC — below the B bandreasoning: optional · parameters: include_reasoning, reasoning
CodingBB — next 30% of the cohort—
AgentsCC — below the B bandparameters: structured_outputs, tool_choice, tools
WritingNo measurementoutput: text
ReasoningNo measurementreasoning: optional · parameters: include_reasoning, reasoning
Document analysisNo measurementinput: file
VisionNo measurementinput: image
Image generationNo measurement—
AudioNo measurement—
VideoNo measurement—
EmbeddingsNo measurement—

Evaluations

SourceBenchmarkValueGradeData retrieved
Artificial AnalysisIntelligence index7.4CC — below the B band13.11.2026
Artificial AnalysisCoding index43.9BB — next 30% of the cohort13.11.2026
Artificial AnalysisAgentic index8CC — below the B band13.11.2026
Design Arenamodels · 3dwin rate 41.1% · rank 1101,055EloCC — below the B band13.11.2026
Design Arenamodels · asciiartwin rate 49.3% · rank 521,135EloCC — below the B band13.11.2026
Design Arenamodels · codecategorieswin rate 44.9% · rank 1051,105EloCC — below the B band13.11.2026
Design Arenamodels · datavizwin rate 45.7% · rank 971,122EloCC — below the B band13.11.2026
Design Arenamodels · gamedevwin rate 44.7% · rank 1011,088EloCC — below the B band13.11.2026
Design Arenamodels · svgwin rate 39.1% · rank 881,017EloCC — below the B band13.11.2026
Design Arenamodels · uicomponentwin rate 42.6% · rank 1031,091EloCC — below the B band13.11.2026
Design Arenamodels · websitewin rate 45.1% · rank 1061,115EloCC — below the B band13.11.2026
How grades work

Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.

  • S — S — top 10% of the cohort
  • A — A — next 20% of the cohort
  • B — B — next 30% of the cohort
  • C — C — below the B band

Providers

Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.

ProviderContext lengthPrice in /1MPrice out /1MLatency p50 (30m, s)Throughput p50 (30m, tok/s)Uptime (30m)
Anthropic200,000$0.500$2.5———

Provider data retrieved: 13.11.2026

Related articles

No published articles identify this model yet.

Links