DeepSeek-V3 vs Gemini 2.5 Flash
DeepSeek vs Google · Prices checked 12 August 2026
Gemini 2.5 Flash is 45 per cent cheaper on blended cost, $0.285 per million tokens against $0.519. A single 100K-input, 10K-output job costs $0.021 on Gemini 2.5 Flash against $0.038 on DeepSeek-V3.
Across the 6 benchmarks both models report, they split the results evenly; neither has a clear capability edge on the public numbers. Gemini 2.5 Flash takes a 1,000,000-token context window against 64,000, giving 15.6× more room for long documents or whole-codebase work.
Pricing and capacity
| Metric | DeepSeek-V3 | Gemini 2.5 Flash | Difference |
|---|---|---|---|
| Input / 1M tokens | $0.270 | $0.150 | 44% |
| Output / 1M tokens | $1.10 | $0.600 | 45% |
| Blended · 70/30calculated | $0.519 | $0.285 | 45% |
| Blended · 50/50calculated | $0.685 | $0.375 | 45% |
| Blended · 80/20calculated | $0.436 | $0.240 | 45% |
| Blended · 20/80calculated | $0.934 | $0.510 | 45% |
| Job cost · 100K + 10Kcalculated | $0.038 | $0.021 | 45% |
| Job cost · 1M + 100Kcalculated | $0.380 | $0.210 | 45% |
| Context window | 64,000 | 1,000,000 | 15.6× |
Input and output rates are as published by each provider. Blended and job-cost rows are calculated comparison metrics, not published prices — how they are derived.
Benchmarks
| Benchmark | DeepSeek-V3 | Gemini 2.5 Flash | Leader |
|---|---|---|---|
| MMLU | 88% | 84% | DeepSeek-V3 |
| GPQA Diamond | 59% | 70% | Gemini 2.5 Flash |
| MATH | 90% | 87% | DeepSeek-V3 |
| HumanEval | 89% | 87% | DeepSeek-V3 |
| SWE-bench Verified | 42% | 48% | Gemini 2.5 Flash |
| LMArena Elo | 1318 Elo | 1325 Elo | Gemini 2.5 Flash |
Only suites both models report are listed, so a missing score is never shown as a loss. Figures are provider-published or from public leaderboards and are not independently re-run.
What each model is for
DeepSeek-V3
DeepSeek · Frontier
Open-weights frontier model that matched GPT-4-class quality at a fraction of the inference cost. Sparked the late-2024 cost reset.
- Frontier quality, open weights
- Aggressive pricing
- Strong code & math
- MoE architecture
Gemini 2.5 Flash
Google · Balanced
Speed-optimised Gemini for high-throughput production. Same multimodal surface as Pro at a fraction of the price.
- Fast
- 1M context
- Native multimodal
- Very cheap
Frequently asked questions
Which is cheaper, DeepSeek-V3 or Gemini 2.5 Flash?
Gemini 2.5 Flash is 45 per cent cheaper on blended cost, $0.285 per million tokens against $0.519. A single 100K-input, 10K-output job costs $0.021 on Gemini 2.5 Flash against $0.038 on DeepSeek-V3. Blended cost weights input at 70% and output at 30%; price your own token split for an exact answer, since the cheaper model on a blended basis is not always cheaper for your workload.
Which performs better, DeepSeek-V3 or Gemini 2.5 Flash?
Across the 6 benchmarks both models report, they split the results evenly; neither has a clear capability edge on the public numbers. These are the figures each provider or public leaderboard publishes, not results we re-run, and a benchmark average can hide the specific behaviour your workload depends on.
Which has the larger context window, DeepSeek-V3 or Gemini 2.5 Flash?
Gemini 2.5 Flash takes a 1,000,000-token context window against 64,000, giving 15.6× more room for long documents or whole-codebase work. The context window caps everything in a single request: prompt, retrieved documents, conversation history and the model’s own output all share it.
Can I compare DeepSeek-V3 and Gemini 2.5 Flash on my own numbers?
Yes. Open both in the side-by-side comparison tool to see every field at once, or use the token calculator to price your actual prompt and monthly request volume against each model. Both are free and need no sign-up.
Price it for your own workload
Related matchups
Terms used on this page
Prices and scores are recomputed on every deploy from the catalogue. Prices checked 12 August 2026.