← All models
DeepSeek R1 vs Gemini 2.5 Pro Preview 05-06
List-price comparison · DeepSeek R1 details · Gemini 2.5 Pro Preview 05-06 details
For a typical workload (100,000 requests / mo), DeepSeek R1 costs 73% less — $146.00/mo vs $550.00/mo.
| DeepSeek R1 | Gemini 2.5 Pro Preview 05-06 | |
|---|---|---|
| Input / 1M tokens | $0.500 | $1.25 |
| Output / 1M tokens | $2.15 | $10.00 |
| Typical request (1,200 in + 400 out) | $0.0015 | $0.0055 |
| Context window | 163,840 tokens | 1,048,576 tokens |
| Max output | 32,768 tokens | 65,535 tokens |
| Tier | Flagship | Flagship |
| Provider | DeepSeek |
Projected monthly cost
1,000 requests / month$1.46 vs $5.5010,000 requests / month$14.60 vs $55.00100,000 requests / month$146.00 vs $550.00
Rows open both models in the calculator — adjust volume and token counts there.
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.
Gemini 2.5 Pro Preview 05-06
Auto-synced from OpenRouter — no editorial write-up yet.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.