DeepSeek-V4-Flash-Vision-Exp API pricing
Updated
Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for DeepSeek-V4-Flash-Vision-Exp is DeepInfra (promotional) at USD 0.2156 per 1M input tokens and USD 0.6468 per 1M output tokens. The median across 3 standard prices is USD 0.44 / USD 1.32. Each price is read from the provider's own pricing page.
Does DeepSeek sell DeepSeek-V4-Flash-Vision-Exp directly?
DeepSeek publishes no price for DeepSeek-V4-Flash-Vision-Exp on its own API that we could find, so this page compares hosts only.
DeepSeek-V4-Flash-Vision-Exp model facts
Facts from DeepSeek's model card for deepseek-ai/DeepSeek-V4-Flash-Vision-Exp 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-Vision-Exp) 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 304.6 billion (304,646,824,126) | Hugging Face model API, checked 2026-11-16Quote“"safetensors": { "total": 304646824126 }” |
| 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 |
| Input and output | Image and text in, text out (the card's task tag is image-text-to-text) | DeepSeek model card metadata, checked 2026-11-16Quote“pipeline_tag: image-text-to-text” |
| 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) | 2026-08-31 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-08-31T06:16:18.000Z"” |
DeepSeek-V4-Flash-Vision-Exp 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 2.0× 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 cheapest promodeepseek-ai/DeepSeek-V4-Flash-Vision-ExpNotes and source quotePromotional price, 51% off list (list 0.44 in / 1.32 out). “$0.216 in $0.647 out $0.007 cached / 1M tokens” | USD 0.2156 | USD 0.00686 | USD 0.6468 | USD 0.3234 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | GMI Clouddeepseek-ai/deepseek-v4-flash-vision-expNotes and source quote“Price (per 1M tokens) Input $0.44 Output $1.32 Cache Read $0.014 Cache Write -” | USD 0.44 | USD 0.014 | USD 1.32 | USD 0.66 | 1,048,575 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | SiliconFlowNotes and source quoteContext shown as 1049K. “DeepSeek-V4-Flash-Vision-Exp 1049K $0.44 $0.028 $1.32” | USD 0.44 | USD 0.028 | USD 1.32 | USD 0.66 | 1,048,576 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spot promodeepseek-ai/DeepSeek-V4-Flash-Vision-ExpNotes and source quoteFlex service tier (0.8× standard). Promotional price, 51% off list (list 0.44 in / 1.32 out). “Flex (0.8×) $0.1725 $0.5174 $0.0055” | USD 0.1725 | USD 0.0055 | USD 0.5174 | USD 0.2587 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra priority promodeepseek-ai/DeepSeek-V4-Flash-Vision-ExpNotes and source quotePriority service tier (1.5× standard). Promotional price, 51% off list (list 0.44 in / 1.32 out). “Priority (1.5×) $0.3234 $0.9702 $0.0103” | USD 0.3234 | USD 0.0103 | USD 0.9702 | USD 0.4851 | 1,048,576 | FP8 | DeepInfra page 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.
- Promo: the provider's page describes this price as promotional or discounted (DeepInfra). 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 and priority): 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-Vision-Exp 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 (promo) | USD 19.77 | USD 46.42 | USD 126.92 |
| GMI Cloud | USD 40.36 | USD 94.73 | USD 259.02 |
| SiliconFlow | USD 41.11 | USD 95.74 | USD 280.44 |
For the support chatbot, the cheapest price (DeepInfra, USD 19.77 a month) saves USD 20.58 against the median (USD 40.36). For the coding agent the gap is USD 132.10 a month (51% lower).
Which DeepSeek-V4-Flash-Vision-Exp provider is cheapest for your traffic?
DeepInfra has the lowest input price (USD 0.2156) and the lowest output price (USD 0.6468), so it is 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 0.3234 cheapest | USD 0.2451 cheapest | USD 0.1825 cheapest |
| GMI Cloud | USD 0.66 | USD 0.5003 | USD 0.3725 |
| SiliconFlow | USD 0.66 | USD 0.5055 | USD 0.3819 |
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.
All 3 providers publish a cached-input price below the input price: DeepInfra (97% off), GMI Cloud (97% off), SiliconFlow (94% off).
Context windows differ: 1,048,576 tokens at DeepInfra and SiliconFlow; 1,048,575 tokens at GMI Cloud. The cheapest row is not always the one that fits a long prompt.
What does DeepSeek-V4-Flash-Vision-Exp 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-Vision-Exp:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.094 | GMI Cloud |
| Arabic MSA | USD 0.165 | GMI Cloud |
| Hindi | USD 0.254 | GMI Cloud |
| Chinese | USD 0.258 | GMI Cloud |
| Code | USD 0.116 | GMI Cloud |
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.
Estimate your own bill
- LLM API cost calculator with DeepSeek-V4-Flash-Vision-Exp 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-Vision-Exp compare with other DeepSeek models?
The DeepSeek models whose cheapest standard price is closest to DeepSeek-V4-Flash-Vision-Exp's (USD 0.3234 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| DeepSeek-V3.2-Exp | USD 0.27 | USD 0.41 | 163,840 | 2 |
| DeepSeek R1 Distill Llama 70B | USD 0.25 | USD 0.75 | 131,072 | 2 |
| DeepSeek V3.1 | USD 0.25 | USD 0.95 | 163,840 | 7 |
| DeepSeek V3 | USD 0.25 | USD 1 | 163,840 | 3 |
| DeepSeek V3.2 | USD 0.2088 | USD 0.3096 | 163,840 | 11 |
| DeepSeek-V3.1-Terminus | USD 0.27 | USD 1 | 163,840 | 3 |
Priced closest from other makers: GLM 4.5 Air (Z.ai, USD 0.31) · Qwen3.8 27B (Qwen, USD 0.3417) · Qwen3 Next 80B A3B Instruct (Qwen, USD 0.3425).
Compare DeepSeek-V4-Flash-Vision-Exp with
- Qwen3.8 27B vs DeepSeek-V4-Flash-Vision-Exp: API price side by side
Also compared: vs Qwen3.8 27B.
Every DeepSeek-V4-Flash-Vision-Exp 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-Vision-Exp API cost per token?
From USD 0.2156 per 1M input tokens (USD 0.0000002156 per token) and USD 0.6468 per 1M output tokens (USD 0.0000006468 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 0.44 input and USD 1.32 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-Vision-Exp?
Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 0.3234 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-Vision-Exp on its own API?
DeepSeek publishes no price for DeepSeek-V4-Flash-Vision-Exp 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 0.2156 / USD 0.6468 per 1M tokens.
Does DeepSeek-V4-Flash-Vision-Exp have cached input pricing?
All 3 standard prices include one. The lowest is USD 0.00686 per 1M at DeepInfra; the median is USD 0.014. Providers without one bill cached input at the input price. What cached input means.
What is the DeepSeek-V4-Flash-Vision-Exp context window?
Up to 1,048,576 tokens. 1 standard price comes with less, down to 1,048,575 tokens (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-Vision-Exp?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 126.92 a month at DeepInfra, USD 259.02 at the median price and USD 280.44 at SiliconFlow. Try your own numbers.
Is there a batch, flex or priority price for DeepSeek-V4-Flash-Vision-Exp?
Yes: flex / spot from DeepInfra at USD 0.1725 / USD 0.5174; priority from DeepInfra at USD 0.3234 / USD 0.9702 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-Vision-Exp free to use through an API?
No provider in our data lists a free price for DeepSeek-V4-Flash-Vision-Exp 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-Vision-Exp open source, with open weights, and what is its licence?
DeepSeek publishes the weights on Hugging Face as deepseek-ai/DeepSeek-V4-Flash-Vision-Exp, 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-Vision-Exp have?
DeepSeek's model card does not state a total that we found. Hugging Face counts about 304.6 billion (304,646,824,126) parameters in the published weight files of deepseek-ai/DeepSeek-V4-Flash-Vision-Exp. 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-Vision-Exp with the OpenAI SDK?
BroadNet does not serve DeepSeek-V4-Flash-Vision-Exp. 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://api.deepinfra.com/v1/openai, model deepseek-ai/DeepSeek-V4-Flash-Vision-Exp). Each provider page quotes the provider's docs with a check date.