The rate card
| Model | Input /1M | Output /1M | Cached read | Cache write | Batch input | Context |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash | $0.14 | $0.28 | $0.0028 | — | $0.07 | 1000K |
What it costs on real workloads
Realistic monthly cost at 1,000 requests/day with the calculator’s defaults — 8% retries, 40% cache hit rate, 15% infra overhead, per-model tokenizer calibration applied. The same three workloads used across every comparison on this site, so the numbers line up.
| Workload | DeepSeek V4 Flash |
|---|---|
| Simple chatbot | $7/mo |
| Chatbot with history | $16/mo |
| Multi-step agent | $88/mo |
The cheapest row in the catalog, by a distance
On the history-carrying chatbot above, DeepSeek V4 Flash runs $16/mo. GPT-5.4 costs roughly 31× that for the same workload; even Gemini 2.5 Flash, the next cheapest model here, is about 4.5× more. At $0.14/1M input and $0.28/1M output, cost effectively stops being the constraint on your architecture.
A 98% cached-read discount — the steepest here
Cached input bills at $0.0028/1M, roughly 98% below standard input. Every other model in the catalog discounts cached reads by about 90%; this one is closer to 98%. On a workload with a large stable prefix — a long system prompt, a reused document, a growing transcript — the cached portion of your bill rounds to nothing.
The 1000K context window compounds that: long prompts are both cheap to send and nearly free to re-send.
The caveat you have to price in
DeepSeek is a China-based provider, and for many teams that is a decision made outside the cost model entirely — by a procurement policy, a customer contract, a regulator, or a data residency commitment. If you handle personal data, regulated data, or anything a customer agreement covers, review the data policy before the price, because no per-token discount survives a compliance objection.
Where it fits cleanly: internal tooling, non-sensitive bulk processing, prototyping, and offline pipelines over public or synthetic data. Where it usually doesn’t: anything customer-facing under a data-processing agreement that doesn’t list it.
Endpoint naming
The legacy endpoint names deepseek-chat and deepseek-reasoner were retired on 2026-07-24; both had already been routing to V4 Flash beforehand. Use deepseek-v4-flash. If you are reading an older integration guide, that is the substitution to make.
Model DeepSeek V4 Flash against the rest of the catalog on your own workload.
Open the calculator →