AI Rate CardGemma 3 12B IT vs Llama 4 Scout 17B Instruct: API price and specs
Gemma 3 12B IT is 50% cheaper than Llama 4 Scout 17B Instruct on input price.
Gemma 3 12B IT is 50% cheaper than Llama 4 Scout 17B Instruct on output price.
Gemma 3 12B IT is 50% cheaper than Llama 4 Scout 17B Instruct on a 1M-in / 200k-out workload.
Llama 4 Scout 17B Instruct has a 900% larger context than Gemma 3 12B IT.
| Field | Gemma 3 12B IT | Llama 4 Scout 17B Instruct |
|---|---|---|
| Lowest input, per 1M | $0.04 | $0.08 +100% |
| Median input, per 1M | $0.05275 | $0.14 +161.1% |
| Lowest output, per 1M | $0.10 | $0.20 +100% |
| Median output, per 1M | $0.15 | $0.45 +200% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.06 | $0.12 +100% |
| Context | 131K +90% | 1.3M |
| Max output | 131K | 131K |
| Providers | 15 +16.7% | 18 |
| Regions | EU, GLOBAL, US | GLOBAL, US |
| Accepts | image, image/gif, image/jpeg, image/png, image/webp, text | image, image/gif, image/jpeg, image/png, image/webp, text |
| Returns | text | text |
| Type | Text models | Text models |
| Free option | yes | no |
| Cheapest provider | kilo | helicone |
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, amazon-bedrock, cloudflare-workers-ai, deepinfra, edenai, fastrouter, helicone, huggingface, jiekou, kilo, novita, openrouter, trustedrouter
Frequently asked questions
Which is cheaper, Gemma 3 12B IT or Llama 4 Scout 17B Instruct?
Gemma 3 12B IT is 50% cheaper than Llama 4 Scout 17B Instruct on input price. Gemma 3 12B IT is 50% cheaper than Llama 4 Scout 17B Instruct on output price. Gemma 3 12B IT is 50% cheaper than Llama 4 Scout 17B Instruct on a 1M-in / 200k-out workload.
Which has the larger context, Gemma 3 12B IT or Llama 4 Scout 17B Instruct?
Gemma 3 12B IT: 131K tokens; Llama 4 Scout 17B Instruct: 1.3M tokens.
Where can I use both Gemma 3 12B IT and Llama 4 Scout 17B Instruct?
aihubmix, aiml, amazon-bedrock, cloudflare-workers-ai, deepinfra, edenai, fastrouter, helicone, huggingface, jiekou, kilo, novita, openrouter, trustedrouter