BroadRouter

DeepSeek V4 Flash API pricing

Updated

Among the 8 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for DeepSeek V4 Flash is DeepInfra at USD 0.09 per 1M input tokens and USD 0.18 per 1M output tokens. The median across 8 standard prices is USD 0.139 / USD 0.28. Each price is read from the provider's own pricing page.

DeepSeek · slug deepseek-v4-flash · up to 1,048,576 tokens of context · 8 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 2026-05-01 (10 archived price points, 1 list-price change): LLM API price history.

Does DeepSeek sell DeepSeek V4 Flash directly?

DeepSeek publishes no price for DeepSeek V4 Flash on its own API that we could find, so this page compares hosts only.

DeepSeek V4 Flash 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 2.4× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

DeepSeek V4 Flash API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra cheapest
deepseek-ai/DeepSeek-V4-Flash
Notes and source quote
“$0.09 in $0.18 out $0.018 cached / 1M tokens”
USD 0.09USD 0.018USD 0.18USD 0.11251,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2GMI Cloud promo
deepseek-ai/DeepSeek-V4-Flash
Notes and source quote

Promotional price, 35% off list (list 0.14 in / 0.28 out / 0.028 cached).

“Price (per 1M tokens) 35% off Input $0.091 $0.14 Output $0.182 $0.28 Cache Read $0.0182 $0.028 Cache Write -”
USD 0.091USD 0.0182USD 0.182USD 0.11381,048,575FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
3SiliconFlow
Notes and source quote

Context shown as 1049K.

“DeepSeek-V4-Flash 1049K $0.13 $0.028 $0.28”
USD 0.13USD 0.028USD 0.28USD 0.16751,048,576not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
4Venice
deepseek-v4-flash
Notes and source quote

Listed as "DeepSeek V4 Flash 0423".

“| DeepSeek V4 Flash 0423 | `deepseek-v4-flash` | $0.138 | $0.275 | $0.028 | — | Private |”
USD 0.138USD 0.028USD 0.275USD 0.17231,000,000not statedVenice page
checked 2026-11-15
re-checked 2026-11-16
5Baidu
deepseek-v4-flash
Notes and source quote
“DeepSeek-V4-Flash DeepSeek-V4-Flash Inference Service Input 0.14 $/M tokens Cache Hit 0.028 $/M tokens Output 0.28 $/M tokens”
USD 0.14USD 0.028USD 0.28USD 0.1751,048,576not statedBaidu page
checked 2026-11-15
re-checked 2026-11-16
6Featherless
deepseek-ai/DeepSeek-V4-Flash
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.14 / CACHED $0.03 / OUTPUT $0.28”
USD 0.14USD 0.03USD 0.28USD 0.175262,144FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
7Parasail
Notes and source quote
“DeepSeek V4 Flash $0.14 $0.28 $0.07”
USD 0.14USD 0.07USD 0.28USD 0.175not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
8Microsoft Azure
Notes and source quote

Foundry Models serverless (pay-as-you-go), Global deployment. Also sold as "FW DeepSeek V4 Flash" (Fireworks on Azure, Data Zone) at a lower price: input $0.15, cached $0.03, output $0.31.

“DeepSeek-V4 Flash Global $0.19 $0.028 $0.51”
USD 0.19USD 0.028USD 0.51USD 0.27not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot
deepseek-ai/DeepSeek-V4-Flash
Notes and source quote

Flex service tier (0.8× standard).

“Flex (0.8×) $0.072 $0.144 $0.0144”
USD 0.072USD 0.0144USD 0.144USD 0.091,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority
deepseek-ai/DeepSeek-V4-Flash
Notes and source quote

Priority service tier (1.5× standard).

“Priority (1.5×) $0.135 $0.27 $0.027”
USD 0.135USD 0.027USD 0.27USD 0.16881,048,576FP8DeepInfra 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 Flash 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 Flash, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfraUSD 7.45USD 19.12USD 68.04
GMI Cloud (promo)USD 7.53USD 19.33USD 68.80
SiliconFlowUSD 11.23USD 28.06USD 103.14
VeniceUSD 11.43USD 29.33USD 104.85
BaiduUSD 11.59USD 29.74USD 105.84
FeatherlessUSD 11.70USD 29.88USD 108.90
ParasailUSD 13.86USD 32.76USD 170.10
Microsoft AzureUSD 17.53USD 41.59USD 140.04

For the support chatbot, the cheapest price (DeepInfra, USD 7.45 a month) saves USD 4.06 against the median (USD 11.51). For the coding agent the gap is USD 37.30 a month (35% lower).

Which DeepSeek V4 Flash provider is cheapest for your traffic?

DeepInfra has the lowest input price (USD 0.09) and the lowest output price (USD 0.18), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.

DeepSeek V4 Flash: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfraUSD 0.1125 cheapestUSD 0.0855 cheapestUSD 0.0639 cheapest
GMI CloudUSD 0.1138USD 0.08645USD 0.06461
SiliconFlowUSD 0.1675USD 0.1293USD 0.09865
VeniceUSD 0.1723USD 0.131USD 0.098
BaiduUSD 0.175USD 0.133USD 0.0994
FeatherlessUSD 0.175USD 0.1338USD 0.1008

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 2 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 8 providers publish a cached-input price below the input price: DeepInfra (80% off), GMI Cloud (80% off), SiliconFlow (78% off), Venice (80% off), Baidu (80% off) and 3 more.

Context windows differ: 1,048,576 tokens at DeepInfra, SiliconFlow and Baidu; 1,048,575 tokens at GMI Cloud; 1,000,000 tokens at Venice; 262,144 tokens at Featherless. Parasail and Microsoft Azure do not state one. The cheapest row is not always the one that fits a long prompt.

What does DeepSeek V4 Flash 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 Flash:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.019DeepInfra
Arabic MSAUSD 0.034DeepInfra
HindiUSD 0.052DeepInfra
ChineseUSD 0.053DeepInfra
CodeUSD 0.024DeepInfra

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 the DeepSeek model card and may use different settings. BroadRouter is BroadNet's site.

Published benchmark results for DeepSeek V4 Flash, with sources
BenchmarkResultSetting or noteSource
MMLU-Pro (EM)86.2Think Max reasoning modeDeepSeek model card, checked 2026-11-16
GPQA Diamond (Pass@1)88.1Think Max reasoning modeDeepSeek model card, checked 2026-11-16
LiveCodeBench (Pass@1)91.6Think Max reasoning modeDeepSeek model card, checked 2026-11-16
SWE Verified (Resolved)79.0Think Max reasoning modeDeepSeek model card, checked 2026-11-16
Terminal Bench 2.0 (Acc)56.9Think Max reasoning modeDeepSeek model card, checked 2026-11-16

Estimate your own bill

The DeepSeek models whose cheapest standard price is closest to DeepSeek V4 Flash's (USD 0.1125 blended):

DeepSeek models priced closest to DeepSeek V4 Flash
ModelCheapest inputCheapest outputMax contextProviders
DeepSeek R1 Distill Qwen 7BUSD 0.10USD 0.20131,0722
DeepSeek V4 Flash 0731USD 0.06USD 0.181,048,57615
DeepSeek V4.1 Flash 1017USD 0.098USD 0.2941,048,57616
DeepSeek R1 Distill Qwen 14BUSD 0.20USD 0.20131,0722
DeepSeek R1 Distill Llama 8BUSD 0.14USD 0.39131,0722
DeepSeek V4.1 FlashUSD 0.14USD 0.421,048,57616

Priced closest from other makers: Qwen3.5 9B (Qwen, USD 0.1125) · GLM 5.3 Flash (Z.ai, USD 0.1187) · Mistral Small 3.2 24B Instruct (Mistral AI, USD 0.1062).

Compare DeepSeek V4 Flash with

Also compared: vs DeepSeek V4.1 Flash · vs DeepSeek V4 Flash 0731 · vs DeepSeek V4 Pro · vs DeepSeek V3.2.

Every DeepSeek V4 Flash 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 Flash API cost per token?

From USD 0.09 per 1M input tokens (USD 0.00000009 per token) and USD 0.18 per 1M output tokens (USD 0.00000018 per token) at the lowest standard prices we found. The median of 8 standard prices is USD 0.139 input and USD 0.28 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 Flash?

Among the 8 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.1125 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does DeepSeek sell DeepSeek V4 Flash on its own API?

DeepSeek publishes no price for DeepSeek V4 Flash on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is DeepInfra at USD 0.09 / USD 0.18 per 1M tokens.

Does DeepSeek V4 Flash have cached input pricing?

All 8 standard prices include one. The lowest is USD 0.018 per 1M at DeepInfra; the median is USD 0.028. Providers without one bill cached input at the input price. What cached input means.

What is the DeepSeek V4 Flash context window?

Up to 1,048,576 tokens. 3 standard prices come with less, down to 262,144 tokens (Featherless, 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 Flash?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 68.04 a month at DeepInfra, USD 105.34 at the median price and USD 170.10 at Parasail. Try your own numbers.

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

Yes: flex / spot from DeepInfra at USD 0.072 / USD 0.144; priority from DeepInfra at USD 0.135 / USD 0.27 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 Flash free to use through an API?

No provider in our data lists a free price for DeepSeek V4 Flash 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.

How does DeepSeek V4 Flash score on benchmarks?

As published, the DeepSeek model card reports 86.2 on MMLU-Pro (EM), 88.1 on GPQA Diamond (Pass@1) and 91.6 on LiveCodeBench (Pass@1) (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