DeepSeek R1 vs DeepSeek V4 Flash — Side-by-side pricing
Side-by-side API pricing and tokenizer details for DeepSeek R1 (DeepSeek) and DeepSeek V4 Flash (DeepSeek).
Side-by-side pricing
| Feature | DeepSeek R1 | DeepSeek V4 Flash |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Input (per 1M tokens) | $0.550 | $0.140 |
| Output (per 1M tokens) | $2.19 | $0.280 |
| Context caching | No | Yes — 98% off cached tokens |
| Batch API discount | Not available | Not available |
| Context window | 128K tokens | 1M tokens |
| Tokenizer | SentencePiece (Llama) | SentencePiece (Llama) |
ⓘ DeepSeek R1: Retired from DeepSeek's own API on 2026-07-24. Figures reflect third-party hosts and are not vendor-published; verify before relying on them.
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 R1
$0.7130
Input: $0.2750 +Output: $0.4380
DeepSeek V4 Flash
$0.1260
Input: $0.0700 +Output: $0.0560
DeepSeek V4 Flash is 82% cheaper for this workload — saving $0.5870 per month at this volume.
Frequently asked questions
No, DeepSeek V4 Flash is cheaper for the typical workload above. At $0.140/1M input and $0.280/1M output tokens, it costs $0.1260 versus $0.7130 for DeepSeek R1 — a 82% difference.
DeepSeek R1 supports a 128K token context window. DeepSeek V4 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 R1 does not support context caching. It does not offer a batch API discount. DeepSeek V4 Flash supports context caching (98% off repeated tokens). It does not offer a batch API discount.
Yes, both DeepSeek R1 and DeepSeek V4 Flash use the SentencePiece (Llama). The same text produces identical token counts on both models, so any cost difference is purely due to the rate each provider charges per token.
DeepSeek R1 (DeepSeek): $0.55 input / $2.19 output per 1M tokens. DeepSeek V4 Flash (DeepSeek): $0.14 input / $0.28 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 R1 costs $1.8620 per 1M total tokens and DeepSeek V4 Flash costs $0.2520. DeepSeek V4 Flash is 86% cheaper for this pattern. For your exact ratio, paste a real prompt into the calculator above.
DeepSeek R1 has a 128K-token context window — approximately 96K words or ~384 pages of standard text. DeepSeek V4 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