Compare AI models

Specifications
Parameters
671B—
Context window
128k200k
API pricing
Input price
—$0.60
Output price
—$2.20
Cached input price
—$0.11
Cheapest input
—$0.32DeepInfra
Cheapest output
—$1.40DeepInfra
—$168DeepInfra · fp4
Benchmarks
SWE-Bench Verified
49.2%73.8%
LiveCodeBench
65.9%84.9%
GPQA Diamond
71.5%85.7%
Overview
CompanyDeepSeekZ.ai
Release dateJan 20 2025Dec 22 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4.7 leads DeepSeek R1 on 3 of the 3 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond). Only GLM-4.7 has a verified first-party price for an available API: $0.60 per million input tokens and $2.20 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek R1. DeepSeek R1 shipped 336 days before GLM-4.7, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 200k (GLM-4.7).

On SWE-Bench Verified, GLM-4.7 leads at 73.8% vs DeepSeek R1 at 49.2%. On LiveCodeBench, GLM-4.7 leads at 84.9% vs DeepSeek R1 at 65.9%. On GPQA Diamond, GLM-4.7 leads at 85.7% vs DeepSeek R1 at 71.5%.