DeepSeek V4 Pro vs Gemini 3.5 Flash — Side-by-side pricing
Side-by-side API pricing and tokenizer details for DeepSeek V4 Pro (DeepSeek) and Gemini 3.5 Flash (Google).
Side-by-side pricing
| Feature | DeepSeek V4 Pro | Gemini 3.5 Flash |
|---|---|---|
| Provider | DeepSeek | |
| Input (per 1M tokens) | $0.435 | $1.50 |
| Output (per 1M tokens) | $0.870 | $9.00 |
| Context caching | Yes — 99% off cached tokens | Yes — 90% off cached tokens |
| Batch API discount | Not available | 50% off |
| Context window | 1M tokens | 1M tokens |
| Tokenizer | SentencePiece (Llama) | Gemini tokenizer |
Real-world cost example
1,000 API requests per month, each with 500 input tokens and 200 output tokens (500K input + 200K output total).
DeepSeek V4 Pro
$0.3915
Input: $0.2175 +Output: $0.1740
Gemini 3.5 Flash
$2.5500
Input: $0.7500 +Output: $1.8000
DeepSeek V4 Pro is 85% cheaper for this workload — saving $2.1585 per month at this volume.
Frequently asked questions
Yes, DeepSeek V4 Pro is cheaper for the typical workload above. At $0.435/1M input and $0.870/1M output tokens, it costs $0.3915 versus $2.5500 for Gemini 3.5 Flash — a 85% difference. Costs scale linearly with request volume, so larger workloads amplify this gap.
DeepSeek V4 Pro supports a 1M token context window. Gemini 3.5 Flash supports a 1M token context window. A larger context window lets you include more text — documents, conversation history, or code — in a single API call.
DeepSeek V4 Pro supports context caching (99% off repeated tokens). It does not offer a batch API discount. Gemini 3.5 Flash supports context caching (90% off repeated tokens). It offers a 50% Batch API discount.
No, they use different tokenizers. DeepSeek V4 Pro uses the SentencePiece (Llama), while Gemini 3.5 Flash uses Gemini tokenizer. Different tokenizers split text differently, so the same prompt will produce different token counts on each model — the effective cost difference may be larger or smaller than the per-token price difference alone suggests.
DeepSeek V4 Pro (DeepSeek): $0.435 input / $0.87 output per 1M tokens. Gemini 3.5 Flash (Google): $1.5 input / $9 output per 1M tokens. Rates shown before caching or batch discounts.
For an 80% output / 20% input workload — typical for code generation or long-form writing — DeepSeek V4 Pro costs $0.7830 per 1M total tokens and Gemini 3.5 Flash costs $7.5000. DeepSeek V4 Pro is 90% cheaper for this pattern. For your exact ratio, paste a real prompt into the calculator above.
DeepSeek V4 Pro has a 1M-token context window — approximately 750K words or ~3K pages of standard text. Gemini 3.5 Flash has a 1M-token context window — approximately 750K words or ~3K pages. (Estimates assume ~0.75 words per token.)
Calculate costs for your actual prompt
Paste your prompt into the calculator and get exact token counts using each model's real tokenizer — all in your browser.
Open calculator