BroadRouter
Get started

DeepSeek V4 Pro 0813 API pricing

Updated

Among the 15 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for DeepSeek V4 Pro 0813 is Chutes at USD 0.85 per 1M input tokens and USD 2.65 per 1M output tokens. The median across 15 standard prices is USD 1.32 / USD 3.96. DeepSeek's own API charges USD 1.32 / USD 3.96 at peak hours.

DeepSeek · slug deepseek-v4-pro-0813 · up to 1,048,576 tokens of context · 15 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-09-02 (3 archived price points, 0 list-price changes): LLM API price history.

What does DeepSeek charge for DeepSeek V4 Pro 0813?

Input
USD 1.32
Cached input
USD 0.044
Output
USD 3.96
Blended 3:1
USD 1.98

USD per 1M tokens on DeepSeek, model deepseek-v4-pro, standard tier, peak hours; off-peak USD 0.66 input, USD 0.022 cached and USD 1.98 output. Source, checked 2026-11-14.

Is a host cheaper than DeepSeek? Yes. Chutes charges USD 0.85 input and USD 2.65 output per 1M tokens, 34% below DeepSeek's own USD 1.32 / USD 3.96 at peak hours on the 3:1 blend. Off-peak, DeepSeek charges USD 0.66 input, USD 0.022 cached and USD 1.98 output.

DeepSeek V4 Pro 0813 model facts

Facts from DeepSeek's model card for deepseek-ai/DeepSeek-V4-Pro-0813 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 V4 Pro 0813: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (deepseek-ai/DeepSeek-V4-Pro-0813) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 66 .safetensors files listed”
LicenceMIT (mit)DeepSeek model card metadata, checked 2026-11-16
Quote
“license: mit”
Parameters in the weight files (Hugging Face count, not the maker's figure)About 1.65 trillion (1,650,497,936,906)Hugging Face model API, checked 2026-11-16
Quote
“"safetensors": { "total": 1650497936906 }”
Context lengthNot found on DeepSeek's model card when we read it; see the context column in the price tablechecked 2026-11-16
Tool callingNot found on DeepSeek's model card when we read itchecked 2026-11-16
First published on Hugging Face (not necessarily the release date)2026-08-13Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2026-08-13T03:05:06.000Z"”

DeepSeek V4 Pro 0813 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 90% above the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

DeepSeek V4 Pro 0813 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Chutes cheapest
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote
“DeepSeek-V4-Pro-0813 deepseek-ai/DeepSeek-V4-Pro-0813 $0.15 per 1M tokens $0.85 per 1M tokens $2.65 per 1M tokens 1.0M”
USD 0.85USD 0.15USD 2.65USD 1.301,000,000not statedChutes page
checked 2026-11-15
re-checked 2026-11-16
2GMI Cloud promo
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote

Promotional price, 20% off list (list 1.32 in / 3.96 out / 0.044 cached).

“Price (per 1M tokens) 20% off Input $1.056 $1.32 Output $3.168 $3.96 Cache Read $0.0352 $0.044 Cache Write -”
USD 1.056USD 0.0352USD 3.168USD 1.5841,048,575FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
3DeepInfra
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote
“$1.30 in $2.60 out $0.10 cached / 1M tokens”
USD 1.30USD 0.10USD 2.60USD 1.6251,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
4CoreWeave Forge
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote
“DeepSeek V4-Pro-0813 $1.31 $3.96 $0.044”
USD 1.31USD 0.044USD 3.96USD 1.9731,048,576not statedCoreWeave Forge page
checked 2026-11-15
re-checked 2026-11-16
5DeepSeek maker peak price
deepseek-v4-pro
Notes and source quote

Peak-hour price (second price column of the quoted table). Off-peak is half: 0.66 input, 0.022 cached, 1.98 output. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak. API model name deepseek-v4-pro serves DeepSeek-V4-Pro-0813. Context 1M, max output 384K.

“(CACHE HIT) OFF-PEAK $0.003 $0.022 PEAK $0.006 $0.044 1M INPUT TOKENS (CACHE MISS) OFF-PEAK $0.15 $0.66 PEAK $0.3 $1.32 1M OUTPUT TOKENS OFF-PEAK $0.6 $1.98 PEAK $1.2 $3.96”
USD 1.32USD 0.044USD 3.96USD 1.981,000,000not statedDeepSeek page
checked 2026-11-14
re-checked 2026-11-16
6Alibaba Cloud
deepseek-v4-pro-0813
Notes and source quote

International (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.66 input, 1.98 output. Cached price derived from the Context Cache page (https://www.alibabacloud.com/help/en/model-studio/context-cache), checked 2026-11-15: implicit-cache hits bill at 10% of the input price in the International (Singapore) scope.

“deepseek-v4-pro-0813 context caching discount International Busy hours: $1.32 Idle hours: $0.66 Busy hours: $3.96 Idle hours: $1.98”
USD 1.32USD 0.132USD 3.96USD 1.98not statednot statedAlibaba Cloud page
checked 2026-11-14
re-checked 2026-11-16
7Baidu
deepseek-v4-pro-0813
Notes and source quote
“DeepSeek-V4-Pro-0813 DeepSeek-V4-Pro-0813 Inference Service Input 1.32 $/M tokens Cache Hit 0.132 $/M tokens Output 3.96 $/M tokens”
USD 1.32USD 0.132USD 3.96USD 1.981,048,576not statedBaidu page
checked 2026-11-15
re-checked 2026-11-16
8Baseten
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote

Context from the model library page (https://www.baseten.co/library/deepseek-v4-pro-0813/), stated as 1M.

“DeepSeek V4 Pro 0813 $1.32 $0.132 $3.96”
USD 1.32USD 0.132USD 3.96USD 1.981,000,000not statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
9Cloudflare Workers AI
@cf/deepseek-ai/deepseek-v4-pro-0813
Notes and source quote

Cloudflare publishes this USD per-token price alongside the neuron price.

“@cf/deepseek-ai/deepseek-v4-pro-0813 $1.320 per M input tokens $0.044 per M cached input tokens $3.960 per M output tokens”
USD 1.32USD 0.044USD 3.96USD 1.98not statednot statedCloudflare Workers AI page
checked 2026-11-14
re-checked 2026-11-16
10DigitalOcean
Notes and source quote

DigitalOcean-hosted.

“DeepSeek V4 Pro 0813 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$1.32$3.96$0.044”
USD 1.32USD 0.044USD 3.96USD 1.98not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
11Novita AI
deepseek/deepseek-v4-pro-0813
Notes and source quote
“DeepSeek V4 Pro 0813 1M $1.32 /Mt · Cache Read $0.044 /Mt $3.96 /Mt”
USD 1.32USD 0.044USD 3.96USD 1.981,048,576not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
12Perplexity
perplexity/deepseek-v4-pro-0813
Notes and source quote

Hosted by Perplexity ("Perplexity-Hosted Models"); tool calls billed separately.

“`perplexity/deepseek-v4-pro-0813` | 1.32 | 3.96 | 0.044”
USD 1.32USD 0.044USD 3.96USD 1.98not statednot statedPerplexity page
checked 2026-11-15
re-checked 2026-11-16
13SiliconFlow
Notes and source quote

Context shown as 1049K.

“DeepSeek-V4-Pro-0813 1049K $1.32 $0.044 $3.96”
USD 1.32USD 0.044USD 3.96USD 1.981,048,576not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
14Together AI
Notes and source quote

US geo-pinned option: $1.65 in / $4.95 out.

“DeepSeek V4 Pro 0813 $1.32 $0.13 (cached) $3.96”
USD 1.32USD 0.13USD 3.96USD 1.98not statednot statedTogether AI page
checked 2026-11-14
re-checked 2026-11-16
15Venice
deepseek-v4-pro-0813
Notes and source quote
“| DeepSeek V4 Pro 0813 | `deepseek-v4-pro-0813` | $1.65 | $4.95 | $0.165 | — | Private |”
USD 1.65USD 0.165USD 4.95USD 2.4751,000,000not statedVenice page
checked 2026-11-15
re-checked 2026-11-16
—DeepInfra flex / spot
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote

Flex service tier (0.8× standard).

“Flex (0.8×) $1.04 $2.08 $0.08”
USD 1.04USD 0.08USD 2.08USD 1.301,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority
deepseek-ai/DeepSeek-V4-Pro-0813
Notes and source quote

Priority service tier (1.5× standard).

“Priority (1.5×) $1.95 $3.90 $0.15”
USD 1.95USD 0.15USD 3.90USD 2.4381,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does DeepSeek V4 Pro 0813 cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. 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 V4 Pro 0813, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
ChutesUSD 86.40USD 193.35USD 697.50
GMI Cloud (promo)USD 96.94USD 227.46USD 624.10
DeepInfraUSD 99.00USD 264.60USD 738.00
CoreWeave ForgeUSD 120.82USD 282.65USD 777.42
DeepSeek (maker)USD 121.18USD 284.33USD 780.12
Alibaba CloudUSD 125.93USD 290.66USD 914.76
BaiduUSD 125.93USD 290.66USD 914.76
BasetenUSD 125.93USD 290.66USD 914.76
Cloudflare Workers AIUSD 121.18USD 284.33USD 780.12
DigitalOceanUSD 121.18USD 284.33USD 780.12
Novita AIUSD 121.18USD 284.33USD 780.12
PerplexityUSD 121.18USD 284.33USD 780.12
SiliconFlowUSD 121.18USD 284.33USD 780.12
Together AIUSD 125.82USD 290.52USD 911.70
VeniceUSD 157.41USD 363.33USD 1,143

For the support chatbot, the cheapest price (Chutes, USD 86.40 a month) saves USD 34.78 against the median (USD 121.18). For the coding agent the gap is USD 156.02 a month (20% lower). The winner changes with the workload: GMI Cloud wins the cache-heavy agent, Chutes the chatbot.

Which DeepSeek V4 Pro 0813 provider is cheapest for your traffic?

Chutes has the lowest input price (USD 0.85) and DeepInfra the lowest output price (USD 2.60). They cost the same at 0.11 input tokens per output token. With more input than that, as with long prompts or retrieval, Chutes is cheaper; with less, as with long answers, DeepInfra is.

DeepSeek V4 Pro 0813: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
ChutesUSD 1.30 cheapestUSD 1.038 cheapestUSD 0.8275
GMI CloudUSD 1.584USD 1.201USD 0.895
DeepInfraUSD 1.625USD 1.175USD 0.815 cheapest
CoreWeave ForgeUSD 1.973USD 1.498USD 1.118
DeepSeek (maker)USD 1.98USD 1.502USD 1.119
Alibaba CloudUSD 1.98USD 1.534USD 1.178

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 9 dearer providers are in the price table above. 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.

All 15 providers publish a cached-input price below the input price: Chutes (82% off), GMI Cloud (97% off), DeepInfra (92% off), CoreWeave Forge (97% off), DeepSeek (97% off) and 10 more.

Context windows differ: 1,048,576 tokens at DeepInfra, CoreWeave Forge, Baidu and 2 more; 1,048,575 tokens at GMI Cloud; 1,000,000 tokens at Chutes, DeepSeek, Baseten and Venice. Alibaba Cloud, Cloudflare Workers AI, DigitalOcean, Perplexity and Together AI do not state one. The cheapest row is not always the one that fits a long prompt.

What does DeepSeek V4 Pro 0813 cost in other languages?

The same text needs a different number of tokens in each language. With the DeepSeek V4.1 Flash tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for DeepSeek V4 Pro 0813:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.182Chutes
Arabic MSAUSD 0.320Chutes
HindiUSD 0.491Chutes
ChineseUSD 0.498Chutes
CodeUSD 0.224Chutes

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Published benchmark results

BroadNet did not run these benchmarks; results are as published by Epoch AI and may use different settings. BroadRouter is BroadNet's site.

Published benchmark results for DeepSeek V4 Pro 0813, with sources
BenchmarkResultSetting or noteSource
GPQA Diamond0.917Max reasoning setting; Epoch run deepseek-v4-pro-0813_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16

Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).

Estimate your own bill

The DeepSeek models whose cheapest standard price is closest to DeepSeek V4 Pro 0813's (USD 1.30 blended):

DeepSeek models priced closest to DeepSeek V4 Pro 0813
ModelCheapest inputCheapest outputMax contextProviders
DeepSeek V4 ProUSD 0.957USD 1.9141,048,57611
DeepSeek R1USD 0.50USD 2.18163,8404
DeepSeek R1 0528USD 0.385USD 1.625163,8405
DeepSeek R1 Distill Qwen 32BUSD 0.50USD 0.90131,0723
DeepSeek V3 0324USD 0.29USD 1.14131,0723
DeepSeek-V3.1-TerminusUSD 0.27USD 1163,8403

Priced closest from other makers: Hy4 Preview (Tencent, USD 1.251) · Qwen3 235B A22B Thinking 2507 FP8 (Qwen, USD 1.212) · Command A+ (Cohere, USD 1.40).

Compare DeepSeek V4 Pro 0813 with

Also compared: vs GLM 5.3 · vs DeepSeek V4 Pro.

Every DeepSeek V4 Pro 0813 price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the DeepSeek V4 Pro 0813 API cost per token?

From USD 0.85 per 1M input tokens (USD 0.00000085 per token) and USD 2.60 per 1M output tokens (USD 0.0000026 per token) at the lowest standard prices we found, which can come from different providers. The median of 15 standard prices is USD 1.32 input and USD 3.96 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 V4 Pro 0813?

Among the 15 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Chutes, ranked on a blend of 3 input tokens to 1 output token (USD 1.30 per 1M). For input alone the lowest price is USD 0.85 (Chutes); for output alone, USD 2.60 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is DeepSeek V4 Pro 0813 cheaper from a host than from DeepSeek?

Yes. Chutes charges USD 0.85 input and USD 2.65 output per 1M tokens, 34% below DeepSeek's own USD 1.32 / USD 3.96 at peak hours on the 3:1 blend. Off-peak, DeepSeek charges USD 0.66 input, USD 0.022 cached and USD 1.98 output.

Does DeepSeek V4 Pro 0813 have cached input pricing?

All 15 standard prices include one. The lowest is USD 0.0352 per 1M at GMI Cloud; the median is USD 0.044. Providers without one bill cached input at the input price. What cached input means.

What is the DeepSeek V4 Pro 0813 context window?

Up to 1,048,576 tokens. 5 standard prices come with less, down to 1,000,000 tokens (Baseten, Chutes, DeepSeek, Venice and GMI Cloud). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on DeepSeek V4 Pro 0813?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 624.10 a month at GMI Cloud, USD 780.12 at the median price and USD 1,143 at Venice. Try your own numbers.

Is there a batch, flex or priority price for DeepSeek V4 Pro 0813?

Yes: flex / spot from DeepInfra at USD 1.04 / USD 2.08; priority from DeepInfra at USD 1.95 / USD 3.90 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 V4 Pro 0813 free to use through an API?

No provider in our data lists a free price for DeepSeek V4 Pro 0813 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is DeepSeek V4 Pro 0813 open source, with open weights, and what is its licence?

DeepSeek publishes the weights on Hugging Face as deepseek-ai/DeepSeek-V4-Pro-0813, in a public repository with no access gate. The licence, as the DeepSeek model card metadata states it: MIT (mit). 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 V4 Pro 0813 have?

DeepSeek's model card does not state a total that we found. Hugging Face counts about 1.65 trillion (1,650,497,936,906) parameters in the published weight files of deepseek-ai/DeepSeek-V4-Pro-0813. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).

How do I call DeepSeek V4 Pro 0813 with the OpenAI SDK?

BroadNet does not serve DeepSeek V4 Pro 0813. 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: Alibaba Cloud Model Studio (https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1, model deepseek-v4-pro-0813), DeepInfra (https://api.deepinfra.com/v1/openai, model deepseek-ai/DeepSeek-V4-Pro-0813), DeepSeek (https://api.deepseek.com, model deepseek-v4-pro) and Together AI (https://api.together.ai/v1). Each provider page quotes the provider's docs with a check date.

How does DeepSeek V4 Pro 0813 score on benchmarks?

As published, Epoch AI measured 0.917 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity