Compare AI models

Specifications
Parameters
—671B
Context window
200k128k
API pricing
Input price
$1.00—
Output price
$5.00—
Cached input price
$0.10—
Cheapest input
$1.00Amazon Bedrock$0.256DeepInfra
Cheapest output
$5.00Amazon Bedrock$0.712DeepInfra
$450Anthropic list price$103StreamLake
Benchmarks
SWE-Bench Verified
73.3%42%
GPQA Diamond
73%59.1%
Overview
CompanyAnthropicDeepSeek
Release dateOct 15 2025Dec 26 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Haiku 4.5 leads DeepSeek V3 on 2 of the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). Only Claude Haiku 4.5 has a verified first-party price for an available API: $1.00 per million input tokens and $5.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek V3. DeepSeek V3 shipped 293 days before Claude Haiku 4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude Haiku 4.5) vs 128k (DeepSeek V3). Claude Haiku 4.5 is closed, while DeepSeek V3 is open weight.

On SWE-Bench Verified, Claude Haiku 4.5 leads at 73.3% vs DeepSeek V3 at 42%. On GPQA Diamond, Claude Haiku 4.5 leads at 73% vs DeepSeek V3 at 59.1%.