DeepSeek V3.2 API pricing
Updated
The cheapest standard price for DeepSeek V3.2 is GMI Cloud (promotional) at USD 0.2088 per 1M input tokens and USD 0.3096 per 1M output tokens. The median across 11 standard prices is USD 0.33 / USD 0.48. Every price is read from the provider's own pricing page, checked 2026-11-15.
Does DeepSeek sell DeepSeek V3.2 directly?
DeepSeek publishes no price for DeepSeek V3.2 on its own API that we could find, so this page compares hosts only.
DeepSeek V3.2 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 4.3× 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 | GMI Cloud cheapest promodeepseek-ai/DeepSeek-V3.2Notes and source quotePromotional price, 28% off list (list 0.29 in / 0.43 out / 0.03 cached). “Price (per 1M tokens) 28% off Input $0.2088 $0.29 Output $0.3096 $0.43 Cache Read $0.0216 $0.03 Cache Write -” | USD 0.2088 | USD 0.0216 | USD 0.3096 | USD 0.234 | 163,840 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | DeepInfradeepseek-ai/DeepSeek-V3.2Notes and source quote“$0.26 in $0.38 out $0.13 cached / 1M tokens” | USD 0.26 | USD 0.13 | USD 0.38 | USD 0.29 | 163,840 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Featherlessdeepseek-ai/DeepSeek-V3.2Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.264 / CACHED $0.06 / OUTPUT $0.41” | USD 0.264 | USD 0.06 | USD 0.41 | USD 0.3005 | 131,072 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 4 | SiliconFlowNotes and source quoteContext shown as 164K. “DeepSeek-V3.2 164K $0.27 $0.135 $0.42” | USD 0.27 | USD 0.135 | USD 0.42 | USD 0.3075 | 163,840 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 5 | Baidudeepseek-v3.2Notes and source quote“DeepSeek-V3.2 DeepSeek-V3.2 Inference Service Input 0.28 $/M tokens Cache Hit 0.028 $/M tokens Output 0.42 $/M tokens” | USD 0.28 | USD 0.028 | USD 0.42 | USD 0.315 | 131,072 | not stated | Baidu page checked 2026-11-15 re-checked 2026-11-16 |
| 6 | Venicedeepseek-v3.2Notes and source quote“| DeepSeek V3.2 | `deepseek-v3.2` | $0.33 | $0.48 | $0.16 | — | Private |” | USD 0.33 | USD 0.16 | USD 0.48 | USD 0.3675 | 160,000 | not stated | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 7 | DigitalOceanNotes and source quoteDigitalOcean-hosted. “DeepSeek V3.2 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.50$1.60$0.15” | USD 0.50 | USD 0.15 | USD 1.60 | USD 0.775 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 8 | Google Vertex AIdeepseek-v3.2Notes and source quote“DeepSeek-V3.2 Input $0.56 … Output $1.68 … Cache Hit $0.056” | USD 0.56 | USD 0.056 | USD 1.68 | USD 0.84 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| 9 | Microsoft AzureNotes and source quoteFoundry Models serverless (pay-as-you-go), Global deployment. “DeepSeek V3.2 Global $0.58 N/A $1.68” | USD 0.58 | not published | USD 1.68 | USD 0.855 | not stated | not stated | Microsoft Azure page checked 2026-11-14 re-checked 2026-11-16 |
| 10 | Amazon BedrockNotes and source quoteTable headed "Regions: US East (N. Virginia), US East (Ohio) and US West (Oregon)". “DeepSeek v3.2 $ 0.62 $ 1.85” | USD 0.62 | not published | USD 1.85 | USD 0.9275 | not stated | not stated | Amazon Bedrock page checked 2026-11-14 re-checked 2026-11-16 |
| 11 | Chutesdeepseek-ai/DeepSeek-V3.2-TEENotes and source quoteRuns on confidential TEE compute. “DeepSeek-V3.2 deepseek-ai/DeepSeek-V3.2-TEE $0.10 per 1M tokens $1.00 per 1M tokens $1.00 per 1M tokens 131K” | USD 1 | USD 0.10 | USD 1 | USD 1 | 131,072 | FP8 | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| — | Google Vertex AI batchdeepseek-v3.2Notes and source quote“DeepSeek-V3.2 Batch Input $0.28 … Batch Output $0.84” | USD 0.28 | not published | USD 0.84 | USD 0.42 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotdeepseek-ai/DeepSeek-V3.2Notes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.208 $0.304 $0.104” | USD 0.208 | USD 0.104 | USD 0.304 | USD 0.232 | 163,840 | FP4 | 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 (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 (batch and 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 (email to info@broadnet.ai, with this page's link filled in).
What does DeepSeek V3.2 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) |
|---|---|---|---|
| GMI Cloud (promo) | USD 14.26 | USD 41.28 | USD 117.29 |
| DeepInfra | USD 23.22 | USD 58.74 | USD 303.30 |
| Featherless | USD 20.12 | USD 54.82 | USD 199.98 |
| SiliconFlow | USD 24.57 | USD 61.38 | USD 317.25 |
| Baidu | USD 19.15 | USD 55.36 | USD 156.24 |
| Venice | USD 29.16 | USD 74.16 | USD 377.10 |
| DigitalOcean | USD 54.90 | USD 118.80 | USD 508.50 |
| Google Vertex AI | USD 53.42 | USD 123.31 | USD 388.08 |
| Microsoft Azure | USD 82.44 | USD 164.40 | USD 1,195 |
| Amazon Bedrock | USD 89.10 | USD 176.55 | USD 1,283 |
| Chutes | USD 59.40 | USD 190.20 | USD 513.00 |
For the support chatbot, the cheapest price (GMI Cloud, USD 14.26 a month) saves USD 14.90 against the median (USD 29.16). For the coding agent the gap is USD 259.81 a month (69% lower).
Which DeepSeek V3.2 provider is cheapest for your traffic?
GMI Cloud has the lowest input price (USD 0.2088) and the lowest output price (USD 0.3096), 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 |
|---|---|---|---|
| GMI Cloud | USD 0.234 cheapest | USD 0.1638 cheapest | USD 0.1076 cheapest |
| DeepInfra | USD 0.29 | USD 0.2412 | USD 0.2023 |
| Featherless | USD 0.3005 | USD 0.224 | USD 0.1628 |
| SiliconFlow | USD 0.3075 | USD 0.2569 | USD 0.2164 |
| Baidu | USD 0.315 | USD 0.2205 | USD 0.1449 |
| Venice | USD 0.3675 | USD 0.3037 | USD 0.2528 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 5 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.
9 of 11 providers publish a cached-input price below the input price: GMI Cloud (90% off), DeepInfra (50% off), Featherless (77% off), SiliconFlow (50% off), Baidu (90% off) and 4 more. Microsoft Azure and Amazon Bedrock publish none, so cached tokens there bill at the input price.
Context windows differ: 163,840 tokens at GMI Cloud, DeepInfra and SiliconFlow; 160,000 tokens at Venice; 131,072 tokens at Featherless, Baidu and Chutes. DigitalOcean, Google Vertex AI, Microsoft Azure and Amazon Bedrock do not state one. The cheapest row is not always the one that fits a long prompt.
What does DeepSeek V3.2 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 V3.2:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.056 | DeepInfra |
| Arabic MSA | USD 0.098 | DeepInfra |
| Hindi | USD 0.150 | DeepInfra |
| Chinese | USD 0.152 | DeepInfra |
| Code | USD 0.069 | 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.
Estimate your own bill
- LLM API cost calculator with DeepSeek V3.2 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 V3.2 compare with other DeepSeek models?
The DeepSeek models whose cheapest standard price is closest to DeepSeek V3.2's (USD 0.234 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | USD 0.14 | USD 0.42 | 1,048,576 | 16 |
| DeepSeek R1 Distill Llama 8B | USD 0.14 | USD 0.39 | 131,072 | 2 |
| DeepSeek R1 Distill Qwen 14B | USD 0.20 | USD 0.20 | 131,072 | 2 |
| DeepSeek-V3.2-Exp | USD 0.27 | USD 0.41 | 163,840 | 2 |
| DeepSeek-V4-Flash-Vision-Exp | USD 0.2156 | USD 0.6468 | 1,048,576 | 3 |
| DeepSeek V4.1 Flash 1017 | USD 0.098 | USD 0.294 | 1,048,576 | 16 |
Priced closest from other makers: Hy3 (Tencent, USD 0.231) · Qwen3 VL 30B A3B Instruct (Qwen, USD 0.2375) · Command R (Cohere, USD 0.2625).
Compare DeepSeek V3.2 with
- DeepSeek V4 Pro vs DeepSeek V3.2: API price side by side
- Qwen3.8 27B vs DeepSeek V3.2: API price side by side
- DeepSeek V3.2 vs DeepSeek V3.1: API price side by side
- DeepSeek-V3.2-Exp vs DeepSeek V3.2: API price side by side
- DeepSeek V4 Flash vs DeepSeek V3.2: API price side by side
Also compared: vs DeepSeek V4 Pro · vs Qwen3.8 27B · vs DeepSeek V3.1 · vs DeepSeek-V3.2-Exp · vs DeepSeek V4 Flash.
Every DeepSeek V3.2 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 V3.2 API cost per token?
From USD 0.2088 per 1M input tokens (USD 0.0000002088 per token) and USD 0.3096 per 1M output tokens (USD 0.0000003096 per token) at the cheapest standard price. The median of 11 standard prices is USD 0.33 input and USD 0.48 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 V3.2?
GMI Cloud (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 0.234 per 1M). It is also the cheapest on both input and output. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does DeepSeek sell DeepSeek V3.2 on its own API?
DeepSeek publishes no price for DeepSeek V3.2 on its own API that we could find, so there is no maker price to compare. The cheapest host is GMI Cloud at USD 0.2088 / USD 0.3096 per 1M tokens.
Does DeepSeek V3.2 have cached input pricing?
9 of 11 standard prices include one. The lowest is USD 0.0216 per 1M at GMI Cloud; the median is USD 0.10. Providers without one bill cached input at the input price. What cached input means.
What is the DeepSeek V3.2 context window?
Up to 163,840 tokens. 4 standard prices come with less, down to 131,072 tokens (Baidu, Chutes, Featherless and Venice). 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 V3.2?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 117.29 a month at GMI Cloud, USD 377.10 at the median price and USD 1,283 at Amazon Bedrock. Try your own numbers.
Is there a batch, flex or priority price for DeepSeek V3.2?
Yes: batch from Google Vertex AI at USD 0.28 / USD 0.84; flex / spot from DeepInfra at USD 0.208 / USD 0.304 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 V3.2 free to use through an API?
No provider in our data lists a free price for DeepSeek V3.2 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Amazon Bedrock: pricing (checked 2026-11-14)
- Microsoft Azure: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- Chutes: 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)
- Google Vertex AI: pricing (checked 2026-11-14)
- SiliconFlow: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)