text model comparison
DeepSeek V4 Pro vs DeepSeek V4 Flash
DeepSeek V4 Flash costs less than DeepSeek V4 Pro at every mix of input and output — $0.090/M against $0.28/M on input and $0.18/M against $0.55/M on output — so at 100M input and 20M output tokens a month it comes to $12.60 against $39.00, a difference of $26.40, and nothing in this catalogue's rate card makes a price case for DeepSeek V4 Pro on this pairing.
Side by side
| DeepSeek V4 Pro | DeepSeek V4 Flash | |
|---|---|---|
| Our rate — input | $0.28/M | $0.090/M |
| Our rate — output | $0.55/M | $0.18/M |
| Our rate — cached input | $0.055/M | $0.018/M |
| Official rate — input | $0.43/M | $0.14/M |
| Official rate — output | $0.87/M | $0.28/M |
| Below official | 37% | 36% |
| Context window | 160K | 160K |
| Publisher | DeepSeek | DeepSeek |
| Licence | MIT | MIT |
| Released | May 21, 2026 | May 21, 2026 |
| Model id | deepseek/deepseek-v4-pro | deepseek/deepseek-v4-flash |
| Callable today | Yes | Yes |
What it costs, at 100M input and 20M output tokens a month
One volume, both models, this catalogue’s published rates. Your figure will differ; the arithmetic will not, and the ratio of the two columns is the part that transfers to your own numbers.
| Model | At our rates | At official rates |
|---|---|---|
| DeepSeek V4 Pro | $39.00 | $60.90 |
| DeepSeek V4 Flash | $12.60 | $19.60 |
At this volume DeepSeek V4 Flash is $26.40 cheaper than DeepSeek V4 Pro — 68% less. That ordering holds at any ratio of input to output, because the cheaper model is cheaper on every rate rather than on one column.
Excludes cached-input savings, which on a repeated-prefix workload reduce the input side substantially. Cached rates are in the table above and on the pricing page.
When to pick each
Pick DeepSeek V4 Pro
- The catalogue lists it for cost-sensitive batch processing at scale, math and reasoning-heavy evaluation pipelines and agent loops with large repeated system prompts.
Pick DeepSeek V4 Flash
- Input costs $0.090/M against DeepSeek V4 Pro's $0.28/M, which decides the bill on input-heavy work — long documents in, short answers out.
- Output costs $0.18/M against DeepSeek V4 Pro's $0.55/M, which is the whole bill on generation-heavy work where a short brief produces long copy.
- Cached input is $0.018/M against DeepSeek V4 Pro's $0.055/M, and on an agent loop the repeated prefix is most of every request.
- The catalogue lists it for billion-token-scale batch jobs, summarisation and reranking and cheap first-pass filtering before an expensive model.
Every line above is a field in the model catalogue rather than a judgement about output quality. This site publishes no benchmark results, so which model answers your prompts better is a measurement to run on your own traffic — the same key calls both.
Questions
- Which is cheaper, DeepSeek V4 Pro or DeepSeek V4 Flash?
- DeepSeek V4 Flash, at 100M input and 20M output tokens a month: $12.60 against $39.00, a difference of $26.40 — 68% less. That holds at any ratio of input to output on this pairing, because DeepSeek V4 Flash has the lower rate on every column, not just the one the headline quotes. What the arithmetic does not tell you is whether both models do your job to the same standard; that is a measurement on your own prompts, not a number we can publish.
- Can I call both DeepSeek V4 Pro and DeepSeek V4 Flash today?
- Yes — both. Requests naming `deepseek/deepseek-v4-pro` or `deepseek/deepseek-v4-flash` reach a live upstream today and are billed at the rates above. 7 of the 24 models in this catalogue are callable right now; the rest are listed at their intended price and marked, so you find out here rather than from an error at call time.
- What licences are DeepSeek V4 Pro and DeepSeek V4 Flash under?
- Both are MIT — DeepSeek V4 Pro from DeepSeek and DeepSeek V4 Flash from DeepSeek. Licence is therefore not a differentiator on this pairing, which is worth knowing before it becomes the question a legal review opens with. Read the text itself before shipping either; a licence name is a pointer to terms, not a summary of them.
- How do I switch between DeepSeek V4 Pro and DeepSeek V4 Flash?
- Change the model id and nothing else. Both are served from `https://router.xark.io/api/v1` behind the same OpenAI-compatible contract — `deepseek/deepseek-v4-pro` and `deepseek/deepseek-v4-flash` — so the request shape, the streaming frames, the usage block and the error envelope are identical between them. Send an explicit id and no substitution happens underneath you, which is what makes running both and comparing the two on your own traffic a change of one string rather than a migration.
- How do these rates compare with the official ones?
- Both rows are published side by side rather than as a single discount claim. DeepSeek V4 Pro is 37% below DeepSeek's official rate and DeepSeek V4 Flash is 36% below DeepSeek's, which at 100M input and 20M output tokens a month is $39.00 against an official $60.90 for DeepSeek V4 Pro, and $12.60 against $19.60 for DeepSeek V4 Flash. The claim on this site is only that our rate sits below the model publisher's own — not that no one else is cheaper. Where a third-party provider undercuts us on either model, that provider's rate is printed on that model's own page.