GLM-5.2
Open flagship GLM for long-horizon coding agents and million-token context work
Cheapest input
$0.85
$/MTok · models.dev
Cheapest output
$3.10
$/MTok
Context
1M
tokens
Offers
3
1 source
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestzai-org/GLM-5.2-FP8 | Vultr | $0.85 | $3.10 | $0 | 393K |
| models.devzai-org/GLM-5.2-FP8 | GMI Cloud | $0.979 | $3.08 | $0.182 | 1M |
| models.devzai-org/GLM-5.2-FP8 | Ambient | $1.20 | $4.20 | $0.26 | 203K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Released: 2026-06-13Family: glm
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence51.1
- AA coding68.8
- AA agentic43.1
Sources: Arena AI, Artificial Analysis. See /benchmarks.