← Compare models
Open all in the calculator — adjust volume and token counts →
DeepSeek R1 vs Gemma 3 12B
List-price comparison ·DeepSeek R1 details ·Gemma 3 12B details
For a typical workload (100,000 requests / mo), Gemma 3 12B is the cheapest — 92% less than the priciest here ($12.00/mo vs $146.00/mo).
| DeepSeek R1 | Gemma 3 12B | |
|---|---|---|
| Input / 1M tokens | $0.500 | $0.050 |
| Output / 1M tokens | $2.15 | $0.150 |
| Typical request (1,200 in + 400 out) | $0.0015 | $0.0001 |
| Context window | 163,840 tokens | 131,072 tokens |
| Max output | 32,768 tokens | 16,384 tokens |
| Quality score | 84/100 | 70/100 |
| Tier | Flagship | Balanced |
| Provider | DeepSeek |
Projected monthly cost
| Requests / mo | DeepSeek R1 | Gemma 3 12B |
|---|---|---|
| 1,000 | $1.46 | $0.12 |
| 10,000 | $14.60 | $1.20 |
| 100,000 | $146.00 | $12.00 |
DeepSeek R1
Chain-of-thought reasoning competitive with closed flagship models on math and logic benchmarks, at open-weight pricing.
Emits long reasoning traces that inflate output token counts and cost — cap reasoning length or use a distilled variant for latency-sensitive paths.
Gemma 3 12B
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.