<!-- Generated from public website sources; do not edit this file. -->

> DSSUB design reference. Account, payments and API are not connected; prices, policies and setup examples require independent launch verification.

# Token and workload cost comparison

This is a design preview. Account, payment and API services are not connected. You can browse model details, compare design prices, calculate workloads, download configuration templates and explore sample account data. No real key, order or API request is created.

[View service availability](/service-status/index.md).

The subscription figures below use monthly billing and show the recurring monthly charge.

Is a subscription always cheaper? No. Low or irregular usage, unused allowances and cached input can favor pay-as-you-go. Compare costs using the prices, dates and workload assumptions below.

## DeepSeek V4.1 Flash

USD per 1 million tokens

DeepSeek V4.1 Flash prices in USD per 1 million tokens. Subscription prices assume full allowance use.

| Plan / provider | Price / 1M tokens |
| --- | --- |
| Base Subscription · effective price | **$0.0116** |
| Max Subscription · effective price | **$0.0093** |
| Pro Max Subscription · effective price | **$0.0067** |
| Ultra Subscription · effective price | **$0.0091** |
| Point packs Pay as you go | Input: $0.135 Cache read $0.01 Output: $0.55 |
| DeepSeek API Official · Off-peak / peak | Input: $0.15 / $0.30 Cache read $0.003 / $0.006 Output: $0.60 / $1.20 |
| [OpenRouter](https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017) Morph · **FP8** · Flash 1017 | Input: $0.022 Cache read $0.004 Output: $0.40 |
| [Together AI](https://www.together.ai/pricing) Flash 1017 · Serverless · Precision not disclosed | Input: $0.30 Cache read $0.006 Output: $1.20 |
| [Fireworks AI](https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash-1017) Flash 1017 · Serverless · Precision not disclosed | Input: $0.30 Cache read $0.006 Output: $1.20 |
| [SiliconFlow](https://www.siliconflow.com/models/deepseek-v4-1-flash) **FP8** · Global · Flash | Input: $0.15 Cache read $0.003 Output: $0.60 |
| [DeepInfra](https://deepinfra.com/deepseek-ai/DeepSeek-V4.1-Flash-1017/api) **FP8** · Flash 1017 · Standard · 51% off | Input: $0.098 Cache read $0.003 Output: $0.294 |
| [Novita AI](https://novita.ai/models/model-detail/deepseek-deepseek-v4.1-flash-1017) **FP8** · Flash 1017 · Serverless | Input: $0.30 Cache read $0.006 Output: $1.20 |

### Cache read · Reusing input

A cache hit reuses computation for an identical input prefix, such as a repeated system prompt or conversation history. Only the matched input tokens receive the cache-read rate; the rest use the regular input rate. It does not reuse a finished answer or change the model’s numerical precision. Cache availability and rules vary by provider. [About Cache →](/about-cache/index.md)

### **FP8** · Numerical precision

FP8 means 8-bit floating point, used for parts of model inference to reduce memory use and potentially speed up computation. Compared with FP16/BF16, it can introduce numerical differences; the effect on answer quality depends on the model and implementation. A cache hit can happen on an FP8 route too: caching concerns input reuse, while FP8 concerns how numbers are represented. [About FP8 →](/about-fp8/index.md)

Subscription effective price = monthly fee ÷ (7-day token allowance × 30 ÷ 7), shown per 1M tokens. Yearly plans use the annual fee ÷ 12. This assumes full weekly allowance use within the plan’s usage windows; using fewer tokens increases your effective price. Input, cached input and output share one allowance at 1×, so the same effective price applies to each.

## Compare a workload, not just a token price.

Example 30-day workloads with 90% input and 10% output. Each volume is shown without caching and with 80% of input cached.

**Monthly plan: recurring monthly charge.** All amounts below are USD for the whole example workload.

Same token volume and mix · Official Flash rates checked November 5, 2026

| Total tokens / 30 days | Official API Off-peak / peak | Point-pack usage | Base | Max | Pro Max | Ultra |
| --- | --- | --- | --- | --- | --- | --- |
| 10M 0% of input cached | $1.95 / $3.90 | $1.77 | $19.90 | $39.90 | $79.90 | $329.00 |
| 10M 80% of input cached | $0.89 / $1.78 | $0.87 | $19.90 | $39.90 | $79.90 | $329.00 |
| 100M 0% of input cached | $19.50 / $39.00 | $17.65 | $19.90 | $39.90 | $79.90 | $329.00 |
| 100M 80% of input cached | $8.92 / $17.83 | $8.65 | $19.90 | $39.90 | $79.90 | $329.00 |
| 1,000M 0% of input cached | $195.00 / $390.00 | $176.50 | $19.90 | $39.90 | $79.90 | $329.00 |
| 1,000M 80% of input cached | $89.16 / $178.32 | $86.50 | $19.90 | $39.90 | $79.90 | $329.00 |

Calculations normalize the weekly allowance to 30 days using weekly allowance × 30 ÷ 7. Requests use the actual 5-hour and 7-day windows. Point-pack figures show usage charges before pack bonuses. Taxes, payment fees, extra tools and overage are excluded.

API cost = uncached input × input rate + cached input × cache rate + output × output rate, using millions of tokens. Official columns assume all tokens use off-peak or all use peak rates; a mixed schedule falls between those amounts. [Verify current official rates and hours ↗](https://api-docs.deepseek.com/quick_start/pricing/)

What if I use only part of my allowance?

Effective subscription price in USD per 1M tokens at 10%, 30% or 100% of the normalized allowance. The subscription fee stays the same when you use less.

| Plan | 10% used | 30% used | 100% used |
| --- | --- | --- | --- |
| Base | $0.1161 | $0.0387 | $0.0116 |
| Max | $0.0931 | $0.031 | $0.0093 |
| Pro Max | $0.0666 | $0.0222 | $0.0067 |
| Ultra | $0.0914 | $0.0305 | $0.0091 |

Unused quota is not a cash balance. Actual effective price is undefined when no tokens are used.

For low or irregular usage, pay-as-you-go may cost less. A subscription is worth considering when the recurring fee, model features and usage windows fit your work. [Read the plan selection guide →](/docs/choosing-a-plan/index.md)

Point-pack rates are deducted from API credit before pack bonuses. Official rates checked November 5, 2026. [DeepSeek prices & peak hours ↗](https://api-docs.deepseek.com/quick_start/pricing/) · [Plan limits ↗](/docs/usage-limits/index.md)

Provider prices and precision labels checked November 5, 2026; click a provider for its source. OpenRouter uses the named Morph route; other providers show direct API prices. DeepInfra included a 51% promotion at the last check; its cached price is rounded as published. SiliconFlow uses its global Flash listing. Token prices exclude credit-purchase fees and taxes. FP8 labels show the provider’s published precision.

---

HTML source: [DeepSeek Token Price Comparison — USD per 1M Tokens](/compare/)
