DeepSeek V3.2 vs DeepSeek V3.1 API pricing
Updated
DeepSeek V3.2: USD 0.2088 input, USD 0.3096 output per 1M tokens (GMI Cloud, promotional). DeepSeek V3.1: USD 0.25 input, USD 0.95 output per 1M tokens (DeepInfra). At 3 input tokens per output token, DeepSeek V3.1 costs 82% more than DeepSeek V3.2 (USD 0.425 vs USD 0.234 per 1M).
How do DeepSeek V3.2 and DeepSeek V3.1 differ on price?
- Cheapest input price: DeepSeek V3.2 USD 0.2088 against USD 0.25 per 1M tokens, so DeepSeek V3.1 costs 1.2× as much (20% more).
- Cheapest output price: DeepSeek V3.2 USD 0.3096 against USD 0.95 per 1M tokens, so DeepSeek V3.1 costs 3.1× as much.
- Among the 201 indexed models, DeepSeek V3.2 ranks 63rd cheapest and DeepSeek V3.1 87th on the 3:1 blend.
- No input:output mix changes the answer: DeepSeek V3.2 is cheaper at every mix before cache discounts.
- Both list cached-input discounts: DeepSeek V3.2 at 9 standard prices of 11, from USD 0.0216 (GMI Cloud, 90% below that provider's input price); DeepSeek V3.1 at 3 standard prices of 7, from USD 0.06 (Google Vertex AI, 90% below that provider's input price).
- Both state a context window of up to 163,840 tokens.
- DeepSeek V3.2 has 11 providers with a standard price, 4 more than DeepSeek V3.1; 6 providers sell both (GMI Cloud, DeepInfra, SiliconFlow, Featherless and 2 more).
- On one account, GMI Cloud charges USD 0.234 for DeepSeek V3.2 (its cheapest price) and USD 0.4525 for DeepSeek V3.1 (1.06× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for DeepSeek V3.1: its dearest standard price is 5.1× its cheapest, against 4.3× for DeepSeek V3.2.
- DeepSeek V3.2 has a batch price at 1 provider, from USD 0.42 at 3:1 (Google Vertex AI); DeepSeek V3.1 has a batch price at 1 provider, from USD 0.4375 at 3:1 (Google Vertex AI).
- For the one-developer coding agent preset, the gap is USD 2,815 a year in DeepSeek V3.2's favour (DeepSeek V3.2 USD 117.29 a month, DeepSeek V3.1 USD 351.90).
- Per character of input, DeepSeek V3.2 costs 1.04× as much as DeepSeek V3.1 in every measured language, because both use the DeepSeek V4.1 Flash tokenizer.
DeepSeek V3.2 and DeepSeek V3.1 prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | DeepSeek V3.2 | DeepSeek V3.1 |
|---|---|---|
| Model page | DeepSeek V3.2 DeepSeek · 11 providers | DeepSeek V3.1 DeepSeek · 7 providers |
| Cheapest standard price, blended 3:1 | USD 0.234 lower promo USD 0.2088 in / USD 0.3096 out at GMI Cloud GMI Cloud page checked 2026-11-15 | USD 0.425 USD 0.25 in / USD 0.95 out at DeepInfra DeepInfra page checked 2026-11-14 |
| Cheapest input | USD 0.2088 lower promo GMI Cloud source | USD 0.25 DeepInfra source |
| Cheapest cached input | USD 0.0216 lower promo GMI Cloud source | USD 0.06 Google Vertex AI source |
| Cheapest output | USD 0.3096 lower promo GMI Cloud source | USD 0.95 DeepInfra source |
| Cheapest non-promotional price | USD 0.26 / USD 0.38 DeepInfra, USD 0.29 blended source | The cheapest price is not promotional. |
| Maker's own API | DeepSeek publishes no paid standard price on its own API that we found. | DeepSeek publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.33 / USD 0.48 input / output, 11 prices | USD 0.285 / USD 1 input / output, 7 prices |
| Context window | 163,840 tokens, largest stated; from 131,072 at some providers | 163,840 tokens, largest stated; from 131,072 at some providers |
| Providers with a standard price | 11 | 7 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do DeepSeek V3.2 and DeepSeek V3.1 cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | DeepSeek V3.2 | DeepSeek V3.1 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 14.26 GMI Cloud | USD 33.12 DeepInfra | USD 18.86 DeepSeek V3.2 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 41.28 GMI Cloud | USD 65.61 DeepInfra | USD 24.33 DeepSeek V3.2 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 117.29 GMI Cloud | USD 351.90 DeepInfra | USD 234.61 DeepSeek V3.2 lower |
DeepSeek V3.2 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 3× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
DeepSeek V3.2 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below DeepSeek V3.1's, so the input:output ratio never changes the answer.
| Input : output tokens | DeepSeek V3.2 | DeepSeek V3.1 |
|---|---|---|
| 1 : 3 (long answers) | USD 0.2844 lower GMI Cloud | USD 0.775 DeepInfra |
| 1 : 1 | USD 0.2592 lower GMI Cloud | USD 0.60 DeepInfra |
| 3 : 1 (the site’s blend) | USD 0.234 lower GMI Cloud | USD 0.425 DeepInfra |
| 10 : 1 (retrieval, long prompts) | USD 0.218 lower GMI Cloud | USD 0.3136 DeepInfra |
| 30 : 1 (agents, big contexts) | USD 0.2121 lower GMI Cloud | USD 0.2726 DeepInfra |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do DeepSeek V3.2 and DeepSeek V3.1 cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the DeepSeek V4.1 Flash tokenizer for DeepSeek V3.2 (the same one for both, so the gap equals the price gap):
| Content | DeepSeek V3.2 | DeepSeek V3.1 |
|---|---|---|
| English | USD 0.056 DeepInfra | USD 0.054 lower DeepInfra |
| Arabic MSA | USD 0.098 DeepInfra | USD 0.094 lower DeepInfra |
| Egyptian Arabic | USD 0.101 DeepInfra | USD 0.097 lower DeepInfra |
| Hindi | USD 0.150 DeepInfra | USD 0.144 lower DeepInfra |
| Chinese | USD 0.152 DeepInfra | USD 0.147 lower DeepInfra |
| Spanish | USD 0.067 DeepInfra | USD 0.064 lower DeepInfra |
| Code | USD 0.069 DeepInfra | USD 0.066 lower DeepInfra |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- DeepSeek V3.2 API pricing: all 11 providers and other tiers.
- DeepSeek V3.1 API pricing: all 7 providers and other tiers.
- Cost calculator with DeepSeek V3.2 and DeepSeek V3.1 preloaded
- DeepSeek token counter
- Prompt caching calculator
More comparisons: DeepSeek V4 Pro vs DeepSeek V3.2 · Qwen3.8 27B vs DeepSeek V3.2 · DeepSeek-V3.2-Exp vs DeepSeek V3.2 · DeepSeek V4 Flash vs DeepSeek V3.2 · DeepSeek V3.1 vs DeepSeek V3 · every DeepSeek V3.2 comparison · every DeepSeek V3.1 comparison · all 662 price comparisons
Questions
Is DeepSeek V3.2 cheaper than DeepSeek V3.1?
Yes. On a blend of 3 input tokens to 1 output token, DeepSeek V3.2 costs USD 0.234 per 1M tokens and DeepSeek V3.1 USD 0.425, at each model's cheapest standard price. For input alone, DeepSeek V3.2 is cheaper (USD 0.2088 against USD 0.25 per 1M); for output alone, DeepSeek V3.2 is (USD 0.3096 against USD 0.95). This compares price only, not quality.
What do DeepSeek V3.2 and DeepSeek V3.1 cost per 1M tokens?
DeepSeek V3.2: from USD 0.2088 input and USD 0.3096 output at GMI Cloud (promotional); median of 11 standard prices USD 0.33 / USD 0.48. DeepSeek V3.1: from USD 0.25 input and USD 0.95 output at DeepInfra; median of 7 standard prices USD 0.285 / USD 1. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both DeepSeek V3.2 and DeepSeek V3.1?
6 providers have a standard price for both: GMI Cloud (USD 0.234 and USD 0.4525 at 3:1), DeepInfra (USD 0.29 and USD 0.425 at 3:1), SiliconFlow (USD 0.3075 and USD 0.4525 at 3:1), Featherless (USD 0.3005 and USD 0.4637 at 3:1), Google Vertex AI (USD 0.84 and USD 0.875 at 3:1), Microsoft Azure (USD 0.855 and USD 2.158 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.234 and USD 0.425.
Which is cheaper for a coding agent or a chatbot, DeepSeek V3.2 or DeepSeek V3.1?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 117.29 a month on DeepSeek V3.2 (GMI Cloud) against USD 351.90 on DeepSeek V3.1 (DeepInfra), a difference of USD 234.61. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 14.26 a month on DeepSeek V3.2 (GMI Cloud) against USD 33.12 on DeepSeek V3.1 (DeepInfra), a difference of USD 18.86. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of DeepSeek V3.2 and DeepSeek V3.1 change?
DeepSeek V3.2 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below DeepSeek V3.1's, so the input:output ratio never changes the answer.
Do DeepSeek V3.2 and DeepSeek V3.1 have cached input pricing?
DeepSeek V3.2 from USD 0.0216 per 1M cached input tokens (GMI Cloud; 9 of 11 standard prices list a discount). DeepSeek V3.1 from USD 0.06 per 1M cached input tokens (Google Vertex AI; 3 of 7 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, DeepSeek V3.2 or DeepSeek V3.1?
Both go up to 163,840 tokens on the providers that state it.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- GMI Cloud: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- Google Vertex AI: pricing (checked 2026-11-14)
- GMI Cloud: pricing (checked 2026-11-15)
- SiliconFlow: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Featherless: pricing (checked 2026-11-15)
- Microsoft Azure: pricing (checked 2026-11-14)