Compare AI models

Specifications
Context window
1M—
API pricing
Input price
$0.10$1.25
Output price
$0.50$2.50
Cached input price
$0.01$0.20
Cheapest input
$0.10Amazon Bedrock—
Cheapest output
$0.50Amazon Bedrock—
$45.00Anthropic list price$375SpaceXSI list price
Benchmarks
BullshitBench v2
57%56%
ARC-AGI-2
61.25%53.3%
Overview
CompanyAnthropicSpaceXSI
Release dateOct 7 2026Feb 17 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude Haiku 5.5 leads Grok 4.20 Beta on 2 of the 2 benchmarks they both report (BullshitBench v2, ARC-AGI-2). Claude Haiku 5.5 is cheaper on both input and output: $0.10 vs $1.25 per million input tokens, and $0.50 vs $2.50 per million output tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 232 days before Claude Haiku 5.5, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On BullshitBench v2, Claude Haiku 5.5 leads at 57% vs Grok 4.20 Beta at 56%. On ARC-AGI-2, Claude Haiku 5.5 leads at 61.25% vs Grok 4.20 Beta at 53.3%.