DeepSeek V4 Flash 0731 API pricing
Updated
Among the 15 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 tie for the lowest blended standard price for DeepSeek V4 Flash 0731; DeepInfra charges USD 0.06 per 1M input tokens and USD 0.18 per 1M output tokens. The median across 15 standard prices is USD 0.22 / USD 0.66. Each price is read from the provider's own pricing page.
Does DeepSeek sell DeepSeek V4 Flash 0731 directly?
DeepSeek publishes no price for DeepSeek V4 Flash 0731 on its own API that we could find, so this page compares hosts only.
DeepSeek V4 Flash 0731 model facts
Facts from DeepSeek's model card for deepseek-ai/DeepSeek-V4-Flash-0731 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.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (deepseek-ai/DeepSeek-V4-Flash-0731) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 48 .safetensors files listed” |
| Licence | MIT (mit) | DeepSeek model card metadata, checked 2026-11-16Quote“license: mit” |
| Parameters in the weight files (Hugging Face count, not the maker's figure) | About 304.2 billion (304,180,418,494) | Hugging Face model API, checked 2026-11-16Quote“"safetensors": { "total": 304180418494 }” |
| 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) | 2026-07-31 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-07-31T07:30:24.000Z"” |
DeepSeek V4 Flash 0731 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 7.3× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepInfra tied cheapestdeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quote“$0.06 in $0.18 out $0.015 cached / 1M tokens” | USD 0.06 | USD 0.015 | USD 0.18 | USD 0.09 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | Hyperbolic tied cheapestdeepseek-v4-flash-0731Notes and source quoteContext shown on page as "1M" (rounded); stored as the decimal value. “DeepSeek V4 Flash 0731 deepseek-v4-flash-0731 DeepSeek · 1M context · Text $0.06 $0.18 $0.015” | USD 0.06 | USD 0.015 | USD 0.18 | USD 0.09 | 1,000,000 | not stated | Hyperbolic page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Basetendeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quoteContext from the model library page (https://www.baseten.co/library/deepseek-v4-flash-0731/), stated as 1M. “DeepSeek-V4-Flash-0731 $0.13 $0.028 $0.26” | USD 0.13 | USD 0.028 | USD 0.26 | USD 0.1625 | 1,000,000 | not stated | Baseten page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Venicedeepseek-v4-flash-0731Notes and source quote“| DeepSeek V4 Flash 0731 | `deepseek-v4-flash-0731` | $0.13 | $0.26 | $0.028 | — | Private |” | USD 0.13 | USD 0.028 | USD 0.26 | USD 0.1625 | 1,000,000 | not stated | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 5 | CoreWeave Forgedeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quote“DeepSeek V4-Flash-0731 $0.13 $0.27 $0.05” | USD 0.13 | USD 0.05 | USD 0.27 | USD 0.165 | 262,144 | not stated | CoreWeave Forge page checked 2026-11-15 re-checked 2026-11-16 |
| 6 | DigitalOceanNotes and source quoteDigitalOcean-hosted. “DeepSeek V4 Flash 0731 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.14$0.28$0.028” | USD 0.14 | USD 0.028 | USD 0.28 | USD 0.175 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 7 | Featherlessdeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.14 / CACHED $0.03 / OUTPUT $0.28” | USD 0.14 | USD 0.03 | USD 0.28 | USD 0.175 | 262,144 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 8 | SiliconFlowNotes and source quoteContext shown as 1049K. “DeepSeek-V4-Flash-0731 1049K $0.22 $0.014 $0.66” | USD 0.22 | USD 0.014 | USD 0.66 | USD 0.33 | 1,048,576 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 9 | GMI Cloud promodeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quotePromotional price, 35% off list (list 0.44 in / 1.32 out / 0.014 cached). “Price (per 1M tokens) 35% off Input $0.286 $0.44 Output $0.858 $1.32 Cache Read $0.0091 $0.014 Cache Write -” | USD 0.286 | USD 0.0091 | USD 0.858 | USD 0.429 | 1,048,575 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 10 | Alibaba Clouddeepseek-v4-flash-0731Notes and source quoteInternational (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.22 input, 0.66 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-flash-0731 context caching discount International Busy hours: $0.44 Idle hours: $0.22 Busy hours: $1.32 Idle hours: $0.66” | USD 0.44 | USD 0.044 | USD 1.32 | USD 0.66 | not stated | not stated | Alibaba Cloud page checked 2026-11-14 re-checked 2026-11-16 |
| 11 | Baidudeepseek-v4-flash-0731Notes and source quote“DeepSeek-V4-Flash DeepSeek-V4-Flash-0731 Inference Service Input 0.44 $/M tokens Cache Hit 0.044 $/M tokens Output 1.32 $/M tokens” | USD 0.44 | USD 0.044 | USD 1.32 | USD 0.66 | 1,048,576 | not stated | Baidu page checked 2026-11-15 re-checked 2026-11-16 |
| 12 | Chutesdeepseek-ai/DeepSeek-V4-Flash-0731-TEENotes and source quoteRuns on confidential TEE compute. “DeepSeek-V4-Flash-0731 deepseek-ai/DeepSeek-V4-Flash-0731-TEE $0.044 per 1M tokens $0.44 per 1M tokens $1.32 per 1M tokens 1.0M” | USD 0.44 | USD 0.044 | USD 1.32 | USD 0.66 | 1,048,576 | FP8 | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| 13 | Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4-flash-0731Notes and source quoteCloudflare publishes this USD per-token price alongside the neuron price. “@cf/deepseek-ai/deepseek-v4-flash-0731 $0.440 per M input tokens $0.014 per M cached input tokens $1.320 per M output tokens” | USD 0.44 | USD 0.014 | USD 1.32 | USD 0.66 | not stated | not stated | Cloudflare Workers AI page checked 2026-11-14 re-checked 2026-11-16 |
| 14 | Microsoft AzureNotes and source quoteFoundry Models serverless (pay-as-you-go), Global deployment. “DeepSeek V4 Flash 0731 Global $0.44 $0.014 $1.32” | USD 0.44 | USD 0.014 | USD 1.32 | USD 0.66 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| 15 | Novita AIdeepseek/deepseek-v4-flash-0731Notes and source quote“DeepSeek V4 Flash 0731 1M $0.44 /Mt · Cache Read $0.028 /Mt $1.32 /Mt” | USD 0.44 | USD 0.028 | USD 1.32 | USD 0.66 | 1,048,576 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotdeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.048 $0.144 $0.012” | USD 0.048 | USD 0.012 | USD 0.144 | USD 0.072 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra prioritydeepseek-ai/DeepSeek-V4-Flash-0731Notes and source quotePriority service tier (1.5× standard). “Priority (1.5×) $0.09 $0.27 $0.0225” | USD 0.09 | USD 0.0225 | USD 0.27 | USD 0.135 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | Venice fastdeepseek-v4-flash-0731-fastNotes and source quoteFast variant, model ID deepseek-v4-flash-0731-fast. “| DeepSeek V4 Flash 0731 Fast | `deepseek-v4-flash-0731-fast` | $0.35 | $0.70 | $0.0875 | — | Private |” | USD 0.35 | USD 0.0875 | USD 0.70 | USD 0.4375 | 1,000,000 | not stated | Venice page checked 2026-11-15 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.
- Promo: the provider's page describes this price as promotional or discounted (GMI Cloud). It ranks as published, but can end without notice; the row's notes give the list price or end date where the page states one.
- Other tiers (flex / spot, priority and fast): 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 (email to info@broadnet.ai, with this page's link filled in).
What does DeepSeek V4 Flash 0731 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.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| DeepInfra | USD 6.21 | USD 13.86 | USD 55.35 |
| Hyperbolic | USD 6.21 | USD 13.86 | USD 55.35 |
| Baseten | USD 10.87 | USD 27.76 | USD 101.34 |
| Venice | USD 10.87 | USD 27.76 | USD 101.34 |
| CoreWeave Forge | USD 12.24 | USD 29.49 | USD 135.90 |
| DigitalOcean | USD 11.59 | USD 29.74 | USD 105.84 |
| Featherless | USD 11.70 | USD 29.88 | USD 108.90 |
| SiliconFlow | USD 20.56 | USD 47.87 | USD 140.22 |
| GMI Cloud (promo) | USD 26.23 | USD 61.57 | USD 168.36 |
| Alibaba Cloud | USD 41.98 | USD 96.89 | USD 304.92 |
| Baidu | USD 41.98 | USD 96.89 | USD 304.92 |
| Chutes | USD 41.98 | USD 96.89 | USD 304.92 |
| Cloudflare Workers AI | USD 40.36 | USD 94.73 | USD 259.02 |
| Microsoft Azure | USD 40.36 | USD 94.73 | USD 259.02 |
| Novita AI | USD 41.11 | USD 95.74 | USD 280.44 |
For the support chatbot, the cheapest price (DeepInfra and 1 other, tied, USD 6.21 a month) saves USD 14.35 against the median (USD 20.56). For the coding agent the gap is USD 84.87 a month (61% lower).
Which DeepSeek V4 Flash 0731 provider is cheapest for your traffic?
DeepInfra and Hyperbolic share the lowest input price (USD 0.06) and the lowest output price (USD 0.18), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| DeepInfra | USD 0.09 cheapest | USD 0.07312 cheapest | USD 0.05962 cheapest |
| Hyperbolic | USD 0.09 cheapest | USD 0.07312 cheapest | USD 0.05962 cheapest |
| Baseten | USD 0.1625 | USD 0.1242 | USD 0.09365 |
| Venice | USD 0.1625 | USD 0.1242 | USD 0.09365 |
| CoreWeave Forge | USD 0.165 | USD 0.135 | USD 0.111 |
| DigitalOcean | USD 0.175 | USD 0.133 | USD 0.0994 |
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: DeepInfra (75% off), Hyperbolic (75% off), Baseten (78% off), Venice (78% off), CoreWeave Forge (62% off) and 10 more.
Context windows differ: 1,048,576 tokens at DeepInfra, SiliconFlow, Baidu and 2 more; 1,048,575 tokens at GMI Cloud; 1,000,000 tokens at Hyperbolic, Baseten and Venice; 262,144 tokens at CoreWeave Forge and Featherless. DigitalOcean, Alibaba Cloud, Cloudflare Workers AI 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 0731 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 0731:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.013 | DeepInfra |
| Arabic MSA | USD 0.023 | DeepInfra |
| Hindi | USD 0.035 | DeepInfra |
| Chinese | USD 0.035 | DeepInfra |
| Code | USD 0.016 | DeepInfra |
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.
| Benchmark | Result | Setting or note | Source |
|---|---|---|---|
| GPQA Diamond | 0.910 | Max reasoning setting; Epoch run deepseek-v4-flash-0731_max, mean score on a 0 to 1 scale | Epoch 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
- LLM API cost calculator with DeepSeek V4 Flash 0731 preloaded: your traffic and cache rate, against any of 428 models.
- 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: what a higher cache-hit rate saves.
How does DeepSeek V4 Flash 0731 compare with other DeepSeek models?
The DeepSeek models whose cheapest standard price is closest to DeepSeek V4 Flash 0731's (USD 0.09 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| DeepSeek V4 Flash | USD 0.09 | USD 0.18 | 1,048,576 | 8 |
| DeepSeek R1 Distill Qwen 7B | USD 0.10 | USD 0.20 | 131,072 | 2 |
| DeepSeek V4.1 Flash 1017 | USD 0.098 | USD 0.294 | 1,048,576 | 16 |
| DeepSeek R1 Distill Qwen 14B | USD 0.20 | USD 0.20 | 131,072 | 2 |
| DeepSeek R1 Distill Llama 8B | USD 0.14 | USD 0.39 | 131,072 | 2 |
| DeepSeek V4.1 Flash | USD 0.14 | USD 0.42 | 1,048,576 | 16 |
Priced closest from other makers: Ling 3.0 Flash (inclusionAI, USD 0.09) · Ling 3.0 Flash VL (inclusionAI, USD 0.09) · NVIDIA Nemotron 3 Nano 30B A3B (NVIDIA, USD 0.0875).
Compare DeepSeek V4 Flash 0731 with
- DeepSeek V4 Flash 0731 vs Gemma 4 26B A4B: API price side by side
- DeepSeek V4 Flash 0731 vs DeepSeek V4 Flash: API price side by side
Also compared: vs Gemma 4 26B A4B · vs DeepSeek V4 Flash.
Every DeepSeek V4 Flash 0731 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 0731 API cost per token?
From USD 0.06 per 1M input tokens (USD 0.00000006 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 15 standard prices is USD 0.22 input and USD 0.66 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 0731?
Among the 15 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 are tied for the lowest price: DeepInfra and Hyperbolic, each USD 0.09 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.06 (DeepInfra and 1 other, tied); for output alone, USD 0.18 (DeepInfra and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does DeepSeek sell DeepSeek V4 Flash 0731 on its own API?
DeepSeek publishes no price for DeepSeek V4 Flash 0731 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 0.06 / USD 0.18 per 1M tokens.
Does DeepSeek V4 Flash 0731 have cached input pricing?
All 15 standard prices include one. The lowest is USD 0.0091 per 1M at GMI Cloud; 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 0731 context window?
Up to 1,048,576 tokens. 6 standard prices come with less, down to 262,144 tokens (CoreWeave Forge, Featherless, Baseten, Hyperbolic and 2 more). 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 0731?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 55.35 a month at DeepInfra, USD 140.22 at the median price and USD 304.92 at Chutes. Try your own numbers.
Is there a batch, flex or priority price for DeepSeek V4 Flash 0731?
Yes: flex / spot from DeepInfra at USD 0.048 / USD 0.144; priority from DeepInfra at USD 0.09 / USD 0.27; fast from Venice at USD 0.35 / USD 0.70 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 0731 free to use through an API?
No provider in our data lists a free price for DeepSeek V4 Flash 0731 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 Flash 0731 open source, with open weights, and what is its licence?
DeepSeek publishes the weights on Hugging Face as deepseek-ai/DeepSeek-V4-Flash-0731, 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 Flash 0731 have?
DeepSeek's model card does not state a total that we found. Hugging Face counts about 304.2 billion (304,180,418,494) parameters in the published weight files of deepseek-ai/DeepSeek-V4-Flash-0731. 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 Flash 0731 with the OpenAI SDK?
BroadNet does not serve DeepSeek V4 Flash 0731. 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-flash-0731) and DeepInfra (https://api.deepinfra.com/v1/openai, model deepseek-ai/DeepSeek-V4-Flash-0731). Each provider page quotes the provider's docs with a check date.
How does DeepSeek V4 Flash 0731 score on benchmarks?
As published, Epoch AI measured 0.910 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
Sources
- Alibaba Cloud: pricing (checked 2026-11-14)
- Microsoft Azure: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- Baseten: pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- DigitalOcean: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- Hyperbolic: pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- SiliconFlow: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)