Z.ai · open weights

GLM-5.2 API

A 1M-token context window, an MIT licence and the strongest reasoning scores on any card we carry — paid plans only.

Paid plans only. A free key returns 402 on this model id. Plans start at $9/mo and include the rest of the catalogue plus failover when the free network is saturated — see plans.

Billed per token above your plan allowance. Prices verified August 14, 2026. Full market table on /pricing.

Call it

Model id: zai-org/GLM-5.2-FP8 (case-sensitive). Any OpenAI SDK works.

from openai import OpenAI

client = OpenAI(
    base_url="https://router.mingles.ai/v1",
    api_key="sk-your-free-key",
)

resp = client.chat.completions.create(
    model="zai-org/GLM-5.2-FP8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Published benchmarks

Source: Z.ai — GLM-5.2-FP8 model card. Full comparison with sources on /compare/claude-api.

Specs

On a plan

Plans hold a priced allowance, not a token count, so what it buys depends on the model. On GLM-5.2 it works out to roughly: This model needs a paid plan — a free key cannot reach it.

On its own card GLM-5.2 posts the strongest reasoning numbers of anything we serve — 62.1 on SWE-bench Pro against 58.6 for Kimi and 56.2 for MiniMax, and 99.2 on AIME 2026 — with the usual caveat that each figure comes from its own vendor under its own harness, so they are three claims rather than one comparison. One genuine comparison does exist: DeepSeek ran GLM-5.2 under its own harness and beat it on all seven agentic rows both models completed, at about a seventh of the price. So the case for GLM is now the 1M-token context and the reasoning scores, not throughput — and both cards agree on its 81.0 Terminal-Bench 2.1, which is the one number here nobody has to take on trust. It is on paid plans only, and it spends a plan allowance at about ×5.4 — roughly Kimi's rate.

FAQ