---
title: "DeepSeek V3 API pricing: 3 providers compared | BroadRouter"
description: "DeepSeek V3 API price per token from 3 providers: lowest listed USD 0.25 input and USD 0.89 output per 1M tokens. Source linked per row."
url: https://broadrouter.com/llm-api-pricing/deepseek-chat/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# DeepSeek V3 API pricing

Updated 2026-11-14

Among the 3 providers we checked (prices read 2026-11-14), the lowest blended standard price for DeepSeek V3 is SiliconFlow at USD 0.25 per 1M input tokens and USD 1 per 1M output tokens. The median across 3 standard prices is USD 0.32 / USD 1. Each price is read from the provider's own pricing page.

DeepSeek · slug `deepseek-chat` · up to 163,840 tokens of context · 3 providers with a standard price. **Every price is read from the provider's own pricing page** and linked in its row, checked 2026-11-14. No aggregator feed. [Download all prices](https://broadrouter.com/data/llm-api-provider-prices/) (every provider and model, with sources, CSV or JSON). How it compares with the market: the [LLM API price index](https://broadrouter.com/data/llm-api-price-index/). Archived list prices since 2024-05-25 (23 archived price points, 1 list-price change): [LLM API price history](https://broadrouter.com/data/llm-api-price-history/#p-deepseek).

## Does DeepSeek sell DeepSeek V3 directly?

DeepSeek publishes no price for DeepSeek V3 on its own API that we could find, so this page compares hosts only.

## DeepSeek V3 model facts

Facts from DeepSeek's model card for [`deepseek-ai/DeepSeek-V3`](https://huggingface.co/deepseek-ai/DeepSeek-V3) and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

DeepSeek V3: facts as stated by the model card and the Hugging Face model API, with sources
| Fact | As stated | Source |
| --- | --- | --- |
| Open weights | Yes. The weights are in a public Hugging Face repository (deepseek-ai/DeepSeek-V3) with no access gate. | [Hugging Face model API](https://huggingface.co/api/models/deepseek-ai/DeepSeek-V3), checked 2026-11-16 · Quote: “"private": false, "gated": false, 163 .safetensors files listed” |
| Licence | DeepSeek Model License (code: MIT License) | [DeepSeek model card](https://huggingface.co/deepseek-ai/DeepSeek-V3), checked 2026-11-16 · Quote: “The use of DeepSeek-V3 Base/Chat models is subject to the Model License.” |
| Total parameters | 671B | [DeepSeek model card](https://huggingface.co/deepseek-ai/DeepSeek-V3), checked 2026-11-16 · Quote: “671B total parameters with 37B activated for each token” |
| Active parameters per token | 37B | [DeepSeek model card](https://huggingface.co/deepseek-ai/DeepSeek-V3), checked 2026-11-16 · Quote: “671B total parameters with 37B activated for each token” |
| Context length | Not found on DeepSeek's model card when we read it; see the context column in the price table | checked 2026-11-16 |
| Tool calling | Not found on DeepSeek's model card when we read it | checked 2026-11-16 |
| First published on Hugging Face (not necessarily the release date) | 2024-12-25 | [Hugging Face model API](https://huggingface.co/api/models/deepseek-ai/DeepSeek-V3), checked 2026-11-16 · Quote: “"createdAt": "2024-12-25T12:52:23.000Z"” |

## DeepSeek V3 price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 4.6× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

DeepSeek V3 API prices by provider
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | **[SiliconFlow](https://broadrouter.com/llm-api-pricing/providers/siliconflow/)** cheapest · Note: Context shown as 164K. Quote: “DeepSeek-V3 164K $0.25 $1.0” | USD 0.25 | not published | USD 1 | USD 0.4375 | 163,840 | not stated | [SiliconFlow page](https://www.siliconflow.com/pricing) · checked 2026-11-14 · re-checked 2026-11-16 |
| 2 | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** · `deepseek-ai/DeepSeek-V3` · Quote: “$0.32 in $0.89 out / 1M tokens” | USD 0.32 | not published | USD 0.89 | USD 0.4625 | 163,840 | FP4 | [DeepInfra page](https://deepinfra.com/deepseek-ai/DeepSeek-V3) · checked 2026-11-14 · re-checked 2026-11-16 |
| 3 | **[Microsoft Azure](https://broadrouter.com/llm-api-pricing/providers/azure/)** · Note: Foundry Models serverless (pay-as-you-go), Global deployment. Quote: “DeepSeek V3 Global $1.14 N/A $4.56” | USD 1.14 | not published | USD 4.56 | USD 1.995 | not stated | not stated | [Microsoft Azure page](https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/) · checked 2026-11-14 · re-checked 2026-11-16 |
| — | **[DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/)** flex / spot · `deepseek-ai/DeepSeek-V3` · Note: Flex service tier (0.8× standard). Quote: “Flex (0.8×) $0.256 $0.712” | USD 0.256 | not published | USD 0.712 | USD 0.37 | 163,840 | FP4 | [DeepInfra page](https://deepinfra.com/deepseek-ai/DeepSeek-V3) · checked 2026-11-14 · re-checked 2026-11-16 |

-   **Ranked:** standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
-   **Other tiers (flex / spot):** batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
-   **Automated re-check 2026-11-16:** a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
-   **Precision** is shown only where the provider states it; "not stated" is unknown, not full precision.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20DeepSeek%20V3%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fdeepseek-chat%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 does DeepSeek V3 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=deepseek-chat). Providers without a cached price bill cached input at the input price.

-   **Support chatbot:** 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
-   **RAG over documents:** 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
-   **Coding agent (one developer):** 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.

Monthly cost of three workloads on DeepSeek V3, by provider
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
| --- | --- | --- | --- |
| **SiliconFlow** | USD 40.50 | USD 75.00 | USD 540.00 |
| **DeepInfra** | USD 44.82 | USD 90.15 | USD 656.10 |
| **Microsoft Azure** | USD 184.68 | USD 342.00 | USD 2,462 |

For the support chatbot, the cheapest price (SiliconFlow, USD 40.50 a month) saves USD 4.32 against the median (USD 44.82). For the coding agent the gap is USD 116.10 a month (18% lower).

## Which DeepSeek V3 provider is cheapest for your traffic?

SiliconFlow has the lowest input price (USD 0.25) and DeepInfra the lowest output price (USD 0.89). They cost the same at 1.6 input tokens per output token. With more input than that, as with long prompts or retrieval, SiliconFlow is cheaper; with less, as with long answers, DeepInfra is.

DeepSeek V3: price per 1M tokens at 3 input to 1 output, by share of input served from cache
| Provider | No cache hits | 50% cached | 90% cached |
| --- | --- | --- | --- |
| **SiliconFlow** (no cache price) | USD 0.4375 cheapest | USD 0.4375 cheapest | USD 0.4375 cheapest |
| **DeepInfra** (no cache price) | USD 0.4625 | USD 0.4625 | USD 0.4625 |
| **Microsoft Azure** (no cache price) | USD 1.995 | USD 1.995 | USD 1.995 |

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

None of the 3 providers publishes a cached-input discount for DeepSeek V3, so cache hits do not change the ranking.

SiliconFlow and DeepInfra state a context window of 163,840 tokens; Microsoft Azure does not state one.

## Estimate your own bill

-   [LLM API cost calculator with DeepSeek V3 preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=deepseek-chat): your traffic and cache rate, against any of 428 models.
-   [DeepSeek token counter](https://broadrouter.com/tools/deepseek-token-counter/): count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/): what a higher cache-hit rate saves.

## How does DeepSeek V3 compare with other DeepSeek models?

The DeepSeek models whose cheapest standard price is closest to DeepSeek V3's (USD 0.4375 blended):

DeepSeek models priced closest to DeepSeek V3
| Model | Cheapest input | Cheapest output | Max context | Providers |
| --- | --- | --- | --- | --- |
| [DeepSeek V3.1](https://broadrouter.com/llm-api-pricing/deepseek-chat-v3.1/) | USD 0.25 | USD 0.95 | 163,840 | 7 |
| [DeepSeek-V3.1-Terminus](https://broadrouter.com/llm-api-pricing/deepseek-v3.1-terminus/) | USD 0.27 | USD 1 | 163,840 | 3 |
| [DeepSeek V3 0324](https://broadrouter.com/llm-api-pricing/deepseek-chat-v3-0324/) | USD 0.29 | USD 1.14 | 131,072 | 3 |
| [DeepSeek R1 Distill Llama 70B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-llama-70b/) | USD 0.25 | USD 0.75 | 131,072 | 2 |
| [DeepSeek-V4-Flash-Vision-Exp](https://broadrouter.com/llm-api-pricing/deepseek-v4-flash-vision-exp/) | USD 0.2156 | USD 0.6468 | 1,048,576 | 3 |
| [DeepSeek R1 Distill Qwen 32B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-qwen-32b/) | USD 0.50 | USD 0.90 | 131,072 | 3 |

Priced closest from other makers: [Qwen3 Coder 480B A35B](https://broadrouter.com/llm-api-pricing/qwen3-coder/) (Qwen, USD 0.4375) · [Step 3.7 Flash](https://broadrouter.com/llm-api-pricing/step-3.7-flash/) (StepFun, USD 0.4375) · [MiniMax M2.5](https://broadrouter.com/llm-api-pricing/minimax-m2.5/) (MiniMax, USD 0.44).

## Compare DeepSeek V3 with

-   [DeepSeek V3.1 vs DeepSeek V3](https://broadrouter.com/llm-api-pricing/compare/deepseek-chat-v3.1-vs-deepseek-chat/): API price side by side
-   [DeepSeek V3 0324 vs DeepSeek V3](https://broadrouter.com/llm-api-pricing/compare/deepseek-chat-v3-0324-vs-deepseek-chat/): API price side by side

Also compared: [vs DeepSeek V3.1](https://broadrouter.com/llm-api-pricing/compare/deepseek-chat-v3.1-vs-deepseek-chat/) · [vs DeepSeek V3 0324](https://broadrouter.com/llm-api-pricing/compare/deepseek-chat-v3-0324-vs-deepseek-chat/).

[Every DeepSeek V3 price comparison](https://broadrouter.com/llm-api-pricing/compare/#m-deepseek-chat) · [All model-vs-model price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

[All 428 models: API prices compared](https://broadrouter.com/llm-api-pricing/) · [Cheapest LLM APIs right now](https://broadrouter.com/llm-api-pricing/cheapest/) · [LLM API price index (open data)](https://broadrouter.com/data/llm-api-price-index/) · [Download all prices (CSV, JSON)](https://broadrouter.com/data/llm-api-provider-prices/) · [Price change log](https://broadrouter.com/llm-api-pricing/changes/)

## Questions

### How much does the DeepSeek V3 API cost per token?

From USD 0.25 per 1M input tokens (USD 0.00000025 per token) and USD 0.89 per 1M output tokens (USD 0.00000089 per token) at the lowest standard prices we found, which can come from different providers. The median of 3 standard prices is USD 0.32 input and USD 1 output. Each price was read from the provider's own pricing page; the source is linked in its row.

### Which provider is cheapest for DeepSeek V3?

Among the 3 providers we checked (prices read 2026-11-14), the lowest is SiliconFlow, ranked on a blend of 3 input tokens to 1 output token (USD 0.4375 per 1M). For input alone the lowest price is USD 0.25 (SiliconFlow); for output alone, USD 0.89 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.

### Does DeepSeek sell DeepSeek V3 on its own API?

DeepSeek publishes no price for DeepSeek V3 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is SiliconFlow at USD 0.25 / USD 1 per 1M tokens.

### Does DeepSeek V3 have cached input pricing?

None of the 3 standard prices includes a cached-input price, so budget repeated prompts at the full input price.

### What is the DeepSeek V3 context window?

163,840 tokens on every provider that states it.

### How much does a coding agent cost per month on DeepSeek V3?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 540.00 a month at SiliconFlow, USD 656.10 at the median price and USD 2,462 at Microsoft Azure. [Try your own numbers](https://broadrouter.com/tools/llm-api-cost-calculator/?model=deepseek-chat).

### Is there a batch, flex or priority price for DeepSeek V3?

Yes: flex / spot from DeepInfra at USD 0.256 / USD 0.712 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.

### Is DeepSeek V3 free to use through an API?

No provider in our data lists a free price for DeepSeek V3 as of 2026-11-14. [Free tiers and credits by provider](https://broadrouter.com/data/llm-api-free-tiers-and-rate-limits/) (checked 2026-11-14) lists general offers that do not name a model; [all free LLM API models](https://broadrouter.com/llm-api-pricing/free/) are on one page.

### Is DeepSeek V3 open source, with open weights, and what is its licence?

DeepSeek publishes the weights on Hugging Face as [`deepseek-ai/DeepSeek-V3`](https://huggingface.co/deepseek-ai/DeepSeek-V3), in a public repository with no access gate. The licence, as the [DeepSeek model card](https://huggingface.co/deepseek-ai/DeepSeek-V3) states it: DeepSeek Model License (code: MIT License). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from DeepSeek's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

### How many parameters does DeepSeek V3 have?

Total parameters, as the [DeepSeek model card](https://huggingface.co/deepseek-ai/DeepSeek-V3) states them: 671B. Active parameters per token: 37B. (checked 2026-11-16; BroadNet did not verify these figures.)

### How do I call DeepSeek V3 with the OpenAI SDK?

BroadNet does not serve DeepSeek V3. Use the OpenAI-compatible base URL of a provider that lists it: create the client with `OpenAI(base_url=..., api_key=...)` and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: [DeepInfra](https://broadrouter.com/llm-api-pricing/providers/deepinfra/) (`https://api.deepinfra.com/v1/openai`, model `deepseek-ai/DeepSeek-V3`). Each provider page quotes the provider's docs with a check date.

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-deepseek-chat&utm_content=page-cta) ·

**Sources**

-   [Microsoft Azure: pricing (checked 2026-11-14)](https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/)
-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/deepseek-ai/DeepSeek-V3)
-   [SiliconFlow: pricing (checked 2026-11-14)](https://www.siliconflow.com/pricing)
