Compare AI models

Specifications
Parameters
671B30B
Context window
128k200k
API pricing
Input price
—$0.00
Output price
—$0.00
Cached input price
—$0.00
—$0.00Z.ai list price
Benchmarks
SWE-Bench Verified
49.2%59.2%
LiveCodeBench
65.9%64%
Overview
CompanyDeepSeekZ.ai
Release dateJan 20 2025Jan 19 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 and GLM-4.7-Flash are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, LiveCodeBench). Only GLM-4.7-Flash has a verified first-party price for an available API: $0.00 per million input tokens and $0.00 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek R1. DeepSeek R1 shipped 364 days before GLM-4.7-Flash, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while GLM-4.7-Flash has 30B. Context windows are 128k (DeepSeek R1) vs 200k (GLM-4.7-Flash).

On SWE-Bench Verified, GLM-4.7-Flash leads at 59.2% vs DeepSeek R1 at 49.2%. On LiveCodeBench, DeepSeek R1 leads at 65.9% vs GLM-4.7-Flash at 64%.