openai/gpt-oss-120b vs z-ai/glm-5.3
For 100,000 calls of 2,000 in and 500 out, openai/gpt-oss-120b is cheaper: $20.53 a month at Baseten, against $83.98 for z-ai/glm-5.3 at OpenRouter — 4.1× the cost.
Cheapest on each
openai/gpt-oss-120b
$20.53/mo
cheapest, at Baseten — $0.1 in, $0.01052 out per million
z-ai/glm-5.3
$83.98/mo
cheapest, at OpenRouter — $0.0699 in, $1.4 out per million
Aligned facts
Same rows on both sides, including the ones we cannot fill.
| Attribute | openai/gpt-oss-120b | z-ai/glm-5.3 |
|---|---|---|
| Context window | 131K | 1M |
| Accepts | Aa | Aa |
| Sellers | 6 | 7 |
| Cheapest input rate | $0.05 / M | $0.0699 / M |
| Cached input rate | $0.075 / M | $0.0689 / 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 | openai/gpt-oss-120b /mo | z-ai/glm-5.3 /mo |
|---|---|---|
| OpenRouter | $60.002026-10-27 | $83.982026-10-27 |
| Baseten | $20.532026-10-22 | $500.002026-10-22 |
| Novita AI | $22.502026-10-22 | $500.002026-10-22 |
| Fireworks AI | $60.002026-10-22 | $500.002026-10-22 |
| SambaNova | $73.502026-10-22 | $500.002026-10-22 |
| Cerebras Inference | $107.502026-10-22 | ○ no answer |
| Together AI | ○ no answer | $500.002026-10-27 |
| FriendliAI | ○ no answer | $500.002026-10-21 |
Cheapest tier per seller, this workload only. In and output rates, and a cached prefix, are broken out in the cost calculator.