AI Rate CardNemotron 3 Super 120B A12B vs GLM-5.3-Flash: API price and specs
Nemotron 3 Super 120B A12B is 44% cheaper than GLM-5.3-Flash on input price.
GLM-5.3-Flash is 69% cheaper than Nemotron 3 Super 120B A12B on output price.
GLM-5.3-Flash is 41% cheaper than Nemotron 3 Super 120B A12B on a 1M-in / 200k-out workload.
GLM-5.3-Flash has a 25% larger context than Nemotron 3 Super 120B A12B.
| Field | Nemotron 3 Super 120B A12B | GLM-5.3-Flash |
|---|---|---|
| Lowest input, per 1M | $0.015 | $0.0269 +79.3% |
| Median input, per 1M | $0.11 | $0.15 +36.4% |
| Lowest output, per 1M | $0.32 +224.6% | $0.0986 |
| Median output, per 1M | $0.60 +20% | $0.50 |
| Lowest unit price | — | $0.033 / request |
| Cost of 1M in + 200k out | $0.079 +69.5% | $0.04662 |
| Context | 1M +20% | 1.3M |
| Max output | 262K +75% | 1M |
| Providers | 20 +69.2% | 65 |
| Regions | EU, GLOBAL, US | APAC, EU, FI, GLOBAL, US |
| Accepts | file, text | application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text, video, video/mp4, video/quicktime, video/webm, video/x-matroska |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | yes | yes |
| Cheapest provider | ollama-cloud | openrouter |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
aihubmix, aiml, cloudflare-workers-ai, deepinfra, edenai, fastrouter, kenari, kilo, nebius, nvidia, ollama, ollama-cloud, opencode, openrouter, perplexity-agent, requesty, synthetic, trustedrouter, vercel
Frequently asked questions
Which is cheaper, Nemotron 3 Super 120B A12B or GLM-5.3-Flash?
Nemotron 3 Super 120B A12B is 44% cheaper than GLM-5.3-Flash on input price. GLM-5.3-Flash is 69% cheaper than Nemotron 3 Super 120B A12B on output price. GLM-5.3-Flash is 41% cheaper than Nemotron 3 Super 120B A12B on a 1M-in / 200k-out workload.
Which has the larger context, Nemotron 3 Super 120B A12B or GLM-5.3-Flash?
Nemotron 3 Super 120B A12B: 1M tokens; GLM-5.3-Flash: 1.3M tokens.
Where can I use both Nemotron 3 Super 120B A12B and GLM-5.3-Flash?
aihubmix, aiml, cloudflare-workers-ai, deepinfra, edenai, fastrouter, kenari, kilo, nebius, nvidia, ollama, ollama-cloud, opencode, openrouter, perplexity-agent, requesty, synthetic, trustedrouter, vercel