Claude Haiku 4.5
by Anthropictext+image+file->text8 endpoints
Neura Intelligence Index
59.0/ 100
Rank
#140—
Confidence
mediumBenchmarks
6(15% coverage)
Overview
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...
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling
Stop sequences
Modalities
Input
TextImageFile
Output
Text
Technical Specifications
Context Window
200K tokens
Max Output
64K tokens
Tokenizer
Claude
Content Moderation
Enabled
Uptime (24h)
10000.0%
Country
🇺🇸US
Release Date
October 15, 202511mo
Supported Parameters
include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Benchmark Performance
general
| Benchmark | Score | Source |
|---|---|---|
| MMMLU | 83 | verified |
coding
| Benchmark | Score | Source |
|---|---|---|
| SWE-bench Verified | 73.3 | verified |
| TerminalBench | 41 | verified |
math
| Benchmark | Score | Source |
|---|---|---|
| AIME 2025 | 80.7 | verified |
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 73 | verified |
agent
| Benchmark | Score | Source |
|---|---|---|
| OSWorld | 50.7 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$1.00
Output$5.00
Cache read$0.10
Cache write$1.25
Added
October 15, 2025
Last synced 9/19/2026