Z.ai: GLM 5

Z.aiOpen weights

Z.ai: GLM 5 by Z.ai costs $0.60 per 1M input tokens and $1.92 per 1M output tokens, with a 205K-token context window.

Pricing

Input (per 1M tokens)

$0.60

Output (per 1M tokens)

$1.92

Cached input (per 1M)

$0.12

Specifications

Provider: Z.ai
Context window: 205K tokens
Parameters: 744B
Released: Feb 2026
Open weights: Yes
Frontier model: No
Hugging Face: zai-org/GLM-5

Benchmarks

LMArena (Chatbot Arena) Elo: 1446.1
LMArena WebDev Elo: 1435.1
SWE-bench Multilingual: 69.7
SWE-bench Verified: 72.8

Speed & latency

Time to first token

1.23s

Output speed

206 tok/s

Fastest host: zai (via vercel-ai-gateway).

Compare Z.ai: GLM 5 with…

Z.ai: GLM 5 vs Z.ai: GLM 5.3 FlashX$1.25/1M Z.ai: GLM 5 vs Z.ai: GLM 5.3 Prime$8.80/1M Z.ai: GLM 5 vs Z.ai: GLM Latest$4.40/1M Z.ai: GLM 5 vs Z.ai: GLM 5V Turbo$4.00/1M Z.ai: GLM 5 vs Z.ai: GLM 5.3 Flash$0.50/1M Z.ai: GLM 5 vs Z.ai: GLM 5.3 Flash (batch)$0.20/1M

FAQ

How much does Z.ai: GLM 5 cost?

Z.ai: GLM 5 is priced at $0.60 per 1M input tokens and $1.92 per 1M output tokens. Output tokens cost more than input.

What is Z.ai: GLM 5's context window?

Z.ai: GLM 5 supports a context window of 205K tokens — the maximum prompt plus response length it can handle in a single request.

Is Z.ai: GLM 5 open weight?

Yes — Z.ai: GLM 5 has openly available weights.

Data as of 2026-10-14. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.