API PRICES

DeepSeek · DeepSeek-V3.2

Provider prices, cheapest first

Browse all models

DeepSeek · DeepSeek-V3.2 official price: not yet recorded. Cheapest inference provider: DeepInfra, input 0.26, output 0.38 USD per million tokens. 75 sites have comparable prices; 140 sites list this model.

Price ranges per million tokens

Inference provider cash prices · Lowest 0.29 · median 0.3025 · highest 0.315 · 2 quotes USD / per million tokens

Inference provider cash prices · Lowest 4.5 · median 4.5 · highest 4.5 · 2 quotes CNY / per million tokens

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

ProviderInputOutputCache readCache writeUnitObservedConditions and source
DeepInfra0.260.380.13—USD / 1M tokens
Official source
OpenRouter · Aggregator0.280.420.028—USD / 1M tokens
Official source
SiliconFlow4.006.000.40—CNY / 1M tokens
Official source
SiliconFlow4.006.000.40—CNY / 1M tokens
Official source

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Filtering by provider: a6api.com

Searching…

Browse all providers
Clear filters

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest — · median — · highest — (0 quotes, USD credits per million total tokens)

sites have comparable prices75140 sites list this model; approximately 0 operators
Lowest input price—USD credits / 1M
Median of each provider’s lowest price—USD credits / 1M

No comparable prices

No prices match the filters. Clear them to see more.

View other prices and terms for this model
Related variants · 56 rows · not ranked

These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.

  • deepseek-v3.2-think (-think · thinking edition): 26 rows
  • deepseek-v3.2-thinking (-thinking · thinking edition): 18 rows
  • DeepSeek-V3.2-thinking (-thinking · thinking edition): 6 rows
  • deepseek/deepseek-v3.2-thinking (-thinking · thinking edition): 4 rows
  • vanchin/deepseek-v3.2-think (-think · thinking edition): 2 rows
  • aws.baby · Alibaba Cloud selected special offers [machine translation]Group on site: 阿里云精选特惠 · vanchin/deepseek-v3.2-think · Input 0.142857142857 / Output 0.214285714286 USD credits / 1M
  • aws.baby · Alibaba Cloud Bailian major clients [machine translation]Group on site: 阿里云百炼大客户 · vanchin/deepseek-v3.2-think · Input 0.228571428571 / Output 0.342857142857 USD credits / 1M
  • llms.best · default · deepseek-v3.2-thinking · Input 0.28 / Output 0.42 USD credits / 1M
  • api.pezayo.com · default · deepseek-v3.2-thinking · Input 0.28572 / Output 0.42365390148 USD credits / 1M
  • api.pezayo.com · official · deepseek-v3.2-thinking · Input 0.28572 / Output 0.42365390148 USD credits / 1M
  • api.bianxie.ai · default · deepseek-v3.2-thinking · Input 0.3 / Output 0.45 USD credits / 1M
  • zen-ai.top · Open source [machine translation]Group on site: 开源 · deepseek-v3.2-thinking · Input 0.8 / Output 1.2 USD credits / 1M
  • api.ai-gaochao.cn · guo_chan · deepseek-v3.2-think · Input 1 / Output 1.5 USD credits / 1M
  • cn.happyapi.org · default · deepseek-v3.2-think · Input 1 / Output 4 USD credits / 1M
  • cn.happyapi.org · vip · deepseek-v3.2-think · Input 1 / Output 4 USD credits / 1M
View all 56 rows →
How this ranking works

All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.

This model has 478 recorded prices; 246 can be compared directly (187 ranked, 59 listed separately). Not comparable yet: price not parsed yet 157, billed per request or another unit 26, display unit not confirmed 15, tiered by rules (see Tiered prices) 14, ratio looks unset 9, scope of the official doc price not confirmed 8

0 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. No recent prices to summarize in this group. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Switch model

FAQ

Which API is cheapest for DeepSeek · DeepSeek-V3.2?

No valid quotes within 10 days. Older quotes are listed as reference prices.

How do I use DeepSeek · DeepSeek-V3.2 in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest DeepSeek · DeepSeek-V3.2 API to Claude Code for me". Install Skill →