DeepSeek: R1 vs Google: Gemini 3 Flash Preview
Head-to-head API pricing and cost comparison between DeepSeek’s DeepSeek: R1 and Google’s Google: Gemini 3 Flash Preview. Prices auto-refresh daily from OpenRouter.
Google: Gemini 3 Flash Preview is 29% cheaper for input tokens; DeepSeek: R1 wins on output tokens at $2.50/1M.
Side-by-side comparison
| Spec | DeepSeek: R1 | Google: Gemini 3 Flash Preview |
|---|---|---|
| Input price (per 1M) | $0.70 | $0.50 |
| Cached input (per 1M) | — | $0.05 |
| Output price (per 1M) | $2.50 | $3.00 |
| Batch input (per 1M) | — | — |
| Batch output (per 1M) | — | — |
| Reasoning price (per 1M) | — | $3.00 |
| Context window | 164K | 1049K |
| Vision support | No | Yes |
| Caching support | No | Yes |
| Batch API | No | No |
| Reasoning capability | No | Yes |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | DeepSeek: R1 | Google: Gemini 3 Flash Preview | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $25.50 | $25.50 | $0.00 Google: Gemini 3 Flash Preview wins |
10K req/day 1500in / 500out tokens | $690.00 | $675.00 | $15.00 Google: Gemini 3 Flash Preview wins |
100K req/day 3000in / 800out tokens | $12,300 | $11,700 | $600.00 Google: Gemini 3 Flash Preview wins |
1M req/day 8000in / 2000out tokens | $318,000 | $300,000 | $18,000 Google: Gemini 3 Flash Preview wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
Frequently asked questions
Which is cheaper, DeepSeek: R1 or Google: Gemini 3 Flash Preview?
For input tokens, Google: Gemini 3 Flash Preview is roughly 29% cheaper at $0.50/1M vs $0.70/1M. For output tokens, DeepSeek: R1 wins at $2.50/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.
What’s the context window difference?
DeepSeek: R1 has a context window of 164K tokens. Google: Gemini 3 Flash Preview offers 1049K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.
Should I use DeepSeek: R1 or Google: Gemini 3 Flash Preview?
Choose DeepSeek: R1 if you’re already on the DeepSeek stack, want broad ecosystem support, or prefer its lower output price. Choose Google: Gemini 3 Flash Preview for Google’s ecosystem, native vision input, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.
How are these prices kept current?
Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: May 28, 2026.