THUDM: GLM 4 32B

Text input Text output Unavailable
Author's Description

GLM-4-32B-0414 is a 32B bilingual (Chinese-English) open-weight language model optimized for code generation, function calling, and agent-style tasks. Pretrained on 15T of high-quality and reasoning-heavy data, it was further refined using human preference alignment, rejection sampling, and reinforcement learning. The model excels in complex reasoning, artifact generation, and structured output tasks, achieving performance comparable to GPT-4o and DeepSeek-V3-0324 across several benchmarks.

Key Specifications
Cost
$$$
Context
32K
Parameters
32B
Released
Apr 17, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Logit Bias Stop Seed Min P Top P Max Tokens Frequency Penalty Temperature Presence Penalty
Performance Summary

THUDM: GLM 4 32B, a 32B bilingual model optimized for code generation, function calling, and agent tasks, consistently performs among the fastest models and offers highly competitive pricing across various benchmarks. Created on April 17, 2025, with a 32000 context length, it demonstrates strong performance in specific areas. The model excels in Email Classification, achieving 99.0% accuracy (87th percentile), and shows good capability in handling Hallucinations with 96.0% accuracy (58th percentile). However, it exhibits significant weaknesses in complex reasoning tasks, scoring only 6.1% in Reasoning (7th percentile), and struggles severely with Instruction Following (0.0% accuracy) and Coding (1.0% accuracy). Its performance in General Knowledge is moderate at 93.5% (38th percentile), while its Ethics score is notably low at 11.0% (10th percentile). Overall, GLM 4 32B presents a mixed profile, showcasing strengths in specific classification and hallucination avoidance, but requiring substantial improvement in areas demanding intricate logical processing, ethical understanding, and precise instruction adherence.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.55
Completion $1.66

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Novita
Novita | thudm/glm-4-32b-0414 32K $0.55 / 1M tokens $1.66 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by thudm