GLM-5 API: pricing, base URL and quick setup

Specifications and pricing

USD per 1M tokens. Final billing depends on your API key group and metered usage.

Cheapest way to use GLM-5

Quick setup

curl https://a2agent.me/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer sk-your-a2agent-key" \
  -d '{
    "model": "glm-5",
    "messages": [{"role": "user", "content": "Reply with OK"}]
  }'

Using it from a coding client

Track prompt size as tool results accumulate. If a session approaches 200K tokens, reduce the context or compare a GLM model with a 1M window.

• Run it in Cline
• Run it in Claude Code

How it compares within its family

These comparisons use catalog context limits, tags and reference rates, not independent quality benchmarks. Rates can change. Check current pricing above and test your workload; a higher price or a larger context window does not establish better results.

GLM-5 is the agent-tagged member of the Z.ai family and the lowest-priced non-Flash GLM model sold here, at $1.00 per million input tokens and $3.20 output. It is also the shortest: 200K, against 1M on GLM-5.2, GLM-5.3 and GLM-5.3 Flash. GLM-5.1 shares the same 200K window but is tagged for coding and lists a little higher, at $1.15 and $4.00. For these Z.ai models, the main catalog differences are price, context length, and tags. GLM-5 is tagged for agents. GLM-5.1 is tagged for coding at the same window size. The 5.2 and 5.3 releases are what you move to when a prompt outgrows 200K. The larger window comes with a higher price per token.

Other models on this platform

• GLM-5.1200K
• GLM-5.21M
• GLM-5.31M
• GLM-5.3 Flash1M

Questions