Anthropic
MultimodalPriced via OpenRouter

Claude Haiku 4.5 (batch)

text+image+file->text

The fastest, cheapest current-gen Claude. Built for high-throughput classification, summarisation and routing.

Claude Haiku 4.5 (batch) is a multimodal AI model from Anthropic. It costs $0.5000 per million input tokens and $2.50 per million output tokens (blended $1.10/M), with a 200,000-token context window.

Profile inherited from upstream Claude Haiku 4.5 ↗ — this is a hosted variant of the same open-weights model.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.5000/M
per million input tokens
OUTPUT
$2.50/M
per million output tokens
BLENDED 70/30
$1.10/M
unchanged since 3 May
CONTEXT
200,000
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Sub-second latency
  • Affordable at scale
  • 200K context
  • Tool calling at speed
Typical use cases
  • Routing & classification
  • Bulk summarisation
  • Realtime UX
  • Edge inference via Bedrock

Benchmarks

vs. best public score
Scores inherited from Claude Haiku 4.5 — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
Graduate-level science questions, "Google-proof". Source: Anthropic (self-reported), GPQA Diamond, read 2026-11-10.
Real GitHub issues solved end-to-end. Source: Anthropic (self-reported), SWE-bench Verified, read 2026-11-10.
LMArena Elo1414 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

Also reported by the provider

Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →

  • MMMLU83%self-reported by Anthropic · 2025-10-15 · Launch table image: average of 10 runs over 14 non-English languages, 128K thinking budget. Not comparable with the MMLU column, so shown here and never ranked.

More from Anthropic

See all 18 →

Frequently asked questions

How much does Claude Haiku 4.5 (batch) cost?

Claude Haiku 4.5 (batch) costs $0.5000 per million input tokens and $2.50 per million output tokens, for a blended reference rate of $1.10 per million tokens.

What is Claude Haiku 4.5 (batch)'s context window?

Claude Haiku 4.5 (batch) supports up to 200,000 tokens of context in a single request.

What is Claude Haiku 4.5 (batch) best for?

Claude Haiku 4.5 (batch) is well suited to Sub-second latency, Affordable at scale and 200K context.

Who makes Claude Haiku 4.5 (batch)?

Claude Haiku 4.5 (batch) is developed and served by Anthropic. It was released in Oct 2025.

Terms used on this page