Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Anthropic models
Anthropic
AnthropicEfficient

Claude Haiku 4.5

Efficient

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

Claude Haiku 4.5 is a efficient AI model from Anthropic. It costs $0.800 per million input tokens and $4.000 per million output tokens (blended $1.760/M), with a 200K-token context window.

Released Oct 2025Modalities text, visionOfficial model page ↗Provider pricing ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$0.800/M
per million input tokens
OUTPUT
$4.000/M
per million output tokens
BLENDED 70/30
$1.760/M
default reference rate · how it's calculated →
CONTEXT
200K
200,000 tokens
What it's 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
MMLU78%
Multitask academic knowledge across 57 subjects.
GPQA Diamond56%
Graduate-level science questions, "Google-proof".
MATH75%
High-school competition math problems.
HumanEval80%
Python function synthesis from docstrings.
SWE-bench Verified38%
Real GitHub issues solved end-to-end.
LMArena Elo1280 Elo
Crowd-sourced head-to-head preference Elo rating.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from Anthropic
See all 16 →
Claude Fable 5
Frontier · 1M ctx
in $10.000/Mout $50.000/M
Claude Opus 4.8
Frontier · 1M ctx
in $5.000/Mout $25.000/M
Claude Opus 4.7
Previous · 1M ctx
in $5.000/Mout $25.000/M
Claude Opus 4.6
Previous · 1M ctx
in $5.000/Mout $25.000/M
Claude Sonnet 4.6
Balanced · 1M ctx
in $3.000/Mout $15.000/M
Claude Opus 4.5
Previous · 200K ctx
in $15.000/Mout $75.000/M
Frequently asked questions

How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs $0.800 per million input tokens and $4.000 per million output tokens, for a blended reference rate of $1.760 per million tokens.

What is Claude Haiku 4.5's context window?

Claude Haiku 4.5 supports up to 200K tokens of context (200,000 tokens).

What is Claude Haiku 4.5 best for?

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

Who makes Claude Haiku 4.5?

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