GLM 5

GLM 5 is a frontier-class, general-purpose large language model optimized for complex systems engineering and long-horizon agentic tasks. It builds on the GLM 4.5 agent-centric lineage and is designed to support multi-step reasoning, math (including AIME-style benchmarks), advanced coding, and tool-augmented workflows, with long context support suitable for sophisticated agents and enterprise applications. Typical uses include autonomous agents for software engineering, data and systems troubleshooting, operations copilots, and high-end chat assistants that must break down complex tasks, call tools reliably, and reason over long sequences of instructions or documents.

Input / 1M tokens$1

Output / 1M tokens$3.2

Maximum context202.8K

Inference providers3

Price comparison

USD per one million tokens, using current provider data.

Provider latency

Last-hour p50 in milliseconds; lower is better.

Provider uptime

Reported availability over the last 24 hours; not a contractual SLA.

Inference providers

Compare current pricing, performance, and privacy across every available provider.

Bedrock

99.95%

Context202.8K

Max output131.1K

p50 latency386 ms

Throughput113.0 t/s

Input price$1

Output price$3.2

Zero retentionNo training

Novita

100.00%

Context202.8K

Max output131.1K

p50 latency980 ms

Throughput129.0 t/s

Input price$1

Output price$3.2

No trainingCaching

Zai

100.00%

Context202.8K

Max output131.1K

p50 latency1,091 ms

Throughput205.0 t/s

Input price$1

Output price$3.2

Caching

Provider	Maximum context	Max output	p50 latency	p50 throughput	24h uptime	Input / 1M tokens	Output / 1M tokens
Bedrock	202.8K	131.1K	386 ms	113.0 t/s	99.954%	$1	$3.2
Novita	202.8K	131.1K	980 ms	129.0 t/s	100.000%	$1	$3.2
Zai	202.8K	131.1K	1,091 ms	205.0 t/s	100.000%	$1	$3.2