Model pricing
DeepSeek V4.1 pricing
DeepSeek V4.1 by DeepSeek costs $0.42 per 1M input tokens and
DeepSeek V4.1 pricing
.68 per 1M output tokens (cached input $0.042, batch input $0.21) as of 2026-09-15. A 1,000-input/500-output request costs $0.00126. The lowest-cost alternative with at least this context window and the same recorded reasoning category is Gemini 4.5 Nano at $0.04/$0.16; capability equivalence is not guaranteed.Notes
Refreshed V4 flagship — sharper agentic coding, 512K context, 90% cache-hit discount
Key pricing facts
| Fact | Value |
|---|---|
| Input / 1M tokens | $0.42 |
| Output / 1M tokens | $1.68 |
| Cached input / 1M | $0.042 |
| Batch input / output / 1M | $0.21 / $0.84 |
| Context window | 512,000 |
| Provider | DeepSeek |
| Last verified | 2026-09-15 |
| Snapshot updated | 2026-09-15 |
Last updated: · Source: DeepSeek pricing · Methodology
Frequently asked questions
What does DeepSeek V4.1 cost per million tokens?
Input costs $0.42 and output costs $1.68 per million tokens. The 1,000-input/500-output example costs $0.00126, before discounts, taxes, hidden reasoning tokens or context-tier surcharges.
Does DeepSeek V4.1 have cached or batch pricing?
Cached input: $0.042 per million tokens under the existing provider cache rules. Batch: $0.21 input and $0.84 output per million tokens. Eligibility and cache-write charges depend on the provider; these discounts are not automatically stacked.
What is a cheaper alternative to DeepSeek V4.1?
Gemini 4.5 Nano costs $0.04 input and $0.16 output per million tokens. This comparison matches context capacity and reasoning category, not benchmark quality. Test your workload before replacing a model.
How often are these prices verified?
The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. Snapshot updated 2026-09-15. The recorded model verification date is 2026-09-15.