---
title: "DeepSeek API pricing per token: 2 models | BroadRouter"
description: "DeepSeek API pricing per 1M tokens for 2 models, from USD 0.30 input, with cached rates, cheapest-host checks and maker price comparison."
url: https://broadrouter.com/llm-api-pricing/providers/deepseek/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# DeepSeek API pricing

Updated 2026-11-14

DeepSeek lists standard prices for 2 models. The cheapest is DeepSeek V4.1 Flash 1017 at USD 0.30 input and USD 1.20 output per 1M tokens; the dearest is DeepSeek V4 Pro 0813 at USD 1.32 / USD 3.96. It publishes cached-input prices for all of them; batch, flex or priority pricing is published as a rule rather than per-model prices (see tiers below).

DeepSeek is a model maker: 2 of the 2 models here are its own. By maker: DeepSeek 2. 2 prices, each read from [DeepSeek's own pricing page](https://api-docs.deepseek.com/quick_start/pricing), checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell DeepSeek's services. Automated re-check 2026-11-16: 2 of 2 prices still matched the provider's page.

Models with a standard price

2

Median input / output

USD 0.81 / USD 2.58

Cached-input prices

2 of 2

Cheapest host for

0 of 2 shared models

## Which models is DeepSeek the cheapest provider for?

None. Every one of the 2 models that DeepSeek shares with other providers is cheaper elsewhere at the standard tier. The closest is [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/), where DeepSeek ranks 5 of 15. It is the dearest provider for 1.

## How does DeepSeek price the most widely hosted models?

The 2 models DeepSeek sells that the most other providers also sell, with DeepSeek's rank among them on the 3:1 blend.

DeepSeek on the most widely hosted models
| Model | DeepSeek | Rank | Cheapest |
| --- | --- | --- | --- |
| [DeepSeek V4.1 Flash 1017](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash-1017/) | USD 0.30 / USD 1.20 | 6 of 16 | DeepInfra USD 0.098 / USD 0.294 |
| [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/) | USD 1.32 / USD 3.96 | 5 of 15 | Chutes USD 0.85 / USD 2.65 |

## DeepSeek price list

USD per 1M tokens: 2 prices for 2 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means DeepSeek is cheaper. DeepSeek is the maker of every model here, so there is no maker price to compare with.

DeepSeek API prices by model
| Model | Tier | Input | Cached | Output | Context | vs maker | Source |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepSeek V4 Pro 0813](https://broadrouter.com/llm-api-pricing/deepseek-v4-pro-0813/) | standard | USD 1.32 | USD 0.044 | USD 3.96 | 1,000,000 | own model | [source](https://api-docs.deepseek.com/quick_start/pricing) |
| [DeepSeek V4.1 Flash 1017](https://broadrouter.com/llm-api-pricing/deepseek-v4.1-flash-1017/) | standard | USD 0.30 | USD 0.006 | USD 1.20 | 1,000,000 | own model | [source](https://api-docs.deepseek.com/quick_start/pricing) |

-   **Cached "—"** means DeepSeek's page shows no cache price for that row; budget cached tokens at the input price.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20DeepSeek%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fproviders%2Fdeepseek%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What service tiers does DeepSeek publish?

DeepSeek publishes no per-model batch, flex or priority prices, but states these rules: Off-peak hours are billed at half the peak prices shown here; each model row's notes give the off-peak price and the peak hours.

Cached input: 2 of 2 standard prices include a cache-read price, a median 3% of the input price. [What cached input means](https://broadrouter.com/glossary/cached-input-tokens/).

**What we recorded about DeepSeek's pricing page:** DeepSeek bills peak and off-peak rates; rows carry the peak (higher) price, with off-peak in notes. Search, fetch, OCR and speech prices left out.

## BroadNet Inference and DeepSeek

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models DeepSeek prices. [BroadNet Inference pricing](https://broadrouter.com/pricing/).

## More on DeepSeek

-   [DeepSeek's own pricing page](https://api-docs.deepseek.com/quick_start/pricing) (the source; checked 2026-11-14)
-   [LLM API free tiers and rate limits](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/): DeepSeek's free tier and default limits next to other providers'
-   [All 41 providers compared](https://broadrouter.com/llm-api-pricing/providers/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [Download every price (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/)

## Quick answers

### Is DeepSeek OpenAI-compatible?

Yes, for chat completions. DeepSeek also documents a separate Anthropic-format URL at /anthropic ([DeepSeek API docs, first API call](https://api-docs.deepseek.com/), checked 2026-11-15).

### What is DeepSeek's API base URL?

`https://api.deepseek.com`, as DeepSeek documents it. There is no version path such as /v1 ([DeepSeek API docs, first API call](https://api-docs.deepseek.com/), checked 2026-11-15).

### Does DeepSeek have a free tier?

No free tier or free credit mentioned on the rate-limit page. Default limits (Default account limit, deepseek-flash): 2,500 concurrent requests. Concurrency limit per account: 2,500 for deepseek-flash, 500 for deepseek-v4-pro; expansion on request at no extra cost ([DeepSeek rate limit docs](https://api-docs.deepseek.com/quick_start/rate_limit), checked 2026-11-14).

## Questions

### How much does the DeepSeek API cost per token?

DeepSeek's standard prices run from USD 0.30 input and USD 1.20 output per 1M tokens (DeepSeek V4.1 Flash 1017) to USD 1.32 / USD 3.96 (DeepSeek V4 Pro 0813). The median across 2 standard prices is USD 0.81 input and USD 2.58 output per 1M, which is USD 0.00000081 per input token. Input, cached input and output are billed separately.

### What is the cheapest model on DeepSeek?

DeepSeek V4.1 Flash 1017, at USD 0.30 input and USD 1.20 output per 1M tokens (USD 0.525 on a 3:1 input-to-output blend).

### Is DeepSeek cheaper than other providers?

It depends on the model. Of 2 models that other providers also price, DeepSeek is the cheapest standard price for none; another provider is cheaper for 2; and it is the dearest for 1. Its median rank is 5.5 of a median 15.5 providers, on a 3:1 input-to-output blend.

### Does DeepSeek have batch, cached or priority pricing?

Cached input: yes, for 2 of 2 standard prices, at a median 3% of the input price. No batch, flex or priority prices are listed per model, but DeepSeek states: Off-peak hours are billed at half the peak prices shown here; each model row's notes give the off-peak price and the peak hours.

### How much does a chatbot cost per month on DeepSeek?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 32.72 on DeepSeek V4.1 Flash 1017 and USD 121.18 on DeepSeek V4 Pro 0813. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/).

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-providers-deepseek&utm_content=page-cta) ·

**Sources**

-   [DeepSeek: pricing page (checked 2026-11-14)](https://api-docs.deepseek.com/quick_start/pricing)
-   [DeepSeek: rate limits and free tier (checked 2026-11-14)](https://api-docs.deepseek.com/quick_start/rate_limit)
-   [DeepSeek API docs, first API call (checked 2026-11-15)](https://api-docs.deepseek.com/)
