~z-ai/glm-flash-latest vs z-ai/glm-4.6v
For 100,000 calls of 2,000 in and 500 out, ~z-ai/glm-flash-latest is cheaper: $9.70 a month at OpenRouter, against $105.00 for z-ai/glm-4.6v at Novita AI — 10.8× the cost.
Cheapest on each
~z-ai/glm-flash-latest
$9.70/mo
cheapest, at OpenRouter — $0.0285 in, $0.08 out per million
z-ai/glm-4.6v
$105.00/mo
cheapest, at Novita AI — $0.3 in, $0.9 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | ~z-ai/glm-flash-latest | z-ai/glm-4.6v |
|---|---|---|
| Context window | 1M | 131K |
| Accepts | Aa · IMG · VID | Aa · IMG · VID |
| Sellers | 1 | 2 |
| Cheapest input rate | $0.0285 / M | $0.3 / M |
| Cached input rate | $0.0285 / M | $0.05 / M |
No quality or benchmark row appears here. We hold no throughput or accuracy measurement for either model, and a cost-per-quality figure built from a lab’s own claim would look authoritative and mean nothing.
Cost for this workload — both models, every seller
100,000 calls a month · 2,000 input and 500 output tokens each. Sellers of both models lead, cheapest combined cost first.
| Seller | ~z-ai/glm-flash-latest /mo | z-ai/glm-4.6v /mo |
|---|---|---|
| OpenRouter | $9.702026-10-27 | $105.002026-10-27 |
| Novita AI | ○ no answer | $105.002026-10-22 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.