GLM 4.6
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Cheapest input
$0.35
$/MTok · models.dev
Cheapest output
$1.54
$/MTok
Context
205K
tokens
Offers
7
3 sources
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.devcheapestz-ai/glm-4.6 | ZenMux | $0.35 | $1.54 | $0.07 | 200K |
| models.devz-ai/glm-4.6 | NanoGPT | $0.4 | $1.50 | $0 | 200K |
| LiteLLMopenrouter/z-ai/glm-4.6 | — | $0.4 | $1.75 | $0.04 | — |
| LiteLLMz-ai/glm-4.6 | — | $0.4 | $1.75 | $0.04 | — |
| OpenRouterz-ai/glm-4.6 | OpenRouter | $0.5 | $2 | $0.1 | 205K |
| models.devz-ai/glm-4.6 | Kilo Gateway | $0.55 | $2.20 | $0.11 | 203K |
| models.devz-ai/glm-4.6 | OrcaRouter | $0.6 | $2.20 | $0.11 | 205K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2025-04Released: 2025-09-30Family: 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 intelligence28.7
- AA coding45.8
- AA agentic17.7
Sources: Arena AI, Artificial Analysis. See /benchmarks.