DeepSeek V3.2 Exp pricing.
Prices checked
DeepSeek V3.2 Exp costs $0.27 in and $0.41 out per million tokens from OpenRouter; the cheapest price is $0.25 at ZenMux, checked .
OpenRouter's own price
OpenRouter
$0.27 in · $0.41 out
65% below the typical price of the 392 text models we track.
Cheapest price
ZenMux
$0.22 in · $0.33 out
19% less than OpenRouter, and the provider says why.
Every provider selling DeepSeek V3.2 Exp
- 1
$0.22 in · $0.33 out · 163k context here
$0.25/M tokens - 2
$0.26 in · $0.38 out
$0.29/M tokens - 3
$0.26 in · $0.38 out
$0.29/M tokens - 4
$0.27 in · $0.41 out
$0.30/M tokens - 5
$0.27 in · $0.41 out
$0.30/M tokens - 6
$0.27 in · $0.41 out
$0.30/M tokens - 7
$0.27 in · $0.41 out
$0.30/M tokens - 8
$0.27 in · $0.41 out
$0.30/M tokens - 9
$0.27 in · $0.41 out
$0.30/M tokens - 10
$0.27 in · $0.40 out
$0.31/M tokens - 11
$0.28 in · $0.42 out
$0.32/M tokens - 12
$0.29 in · $0.43 out · 131k context here
$0.32/M tokens - 13
Qiniu
Costs more$0.29 in · $0.43 out · 128k context here
$0.33/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at ZenMux, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Evidence
Each is a measurement of the stated version and configuration. Two benchmarks are not the same test, and a score is not the chance your own work succeeds.
BFCL V4 multi-turn V4 / bfcl-eval 2025.12.17
37.38 / 100Berkeley BFCL · model DeepSeek-V3.2-Exp · FC; multi-turn
Published 17 Oct 2026, read 31 Oct 2026
Read the sourceBFCL V4 web-search V4 / bfcl-eval 2025.12.17
69.5 / 100Berkeley BFCL · model DeepSeek-V3.2-Exp · FC; web-search
Published 17 Oct 2026, read 31 Oct 2026
Read the sourceBFCL V4 memory V4 / bfcl-eval 2025.12.17
54.19 / 100Berkeley BFCL · model DeepSeek-V3.2-Exp · FC; memory
Published 17 Oct 2026, read 31 Oct 2026
Read the sourceHow we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. DeepSeek trained DeepSeek V3.2 Exp and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Same as maker
- Sold by someone else at the price the maker charges.
- Costs more
- Sold by someone else for more than the maker charges.
Similar models
Models from other labs that do what DeepSeek V3.2 Exp does, cheapest first. Each percentage is against DeepSeek V3.2 Exp's cheapest price, $0.25 per M tokens.
Frequently asked
- Who sells DeepSeek V3.2 Exp cheapest?
- ZenMux, at $0.22 in and $0.33 out per million tokens, checked 31 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Is DeepSeek V3.2 Exp open weights?
- Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V3.2 Exp, which is why 12 providers sell it and why their prices differ so much.
- How much context does DeepSeek V3.2 Exp hold?
- 163,840 tokens in one call, which is about 164k, and it can call your own functions.
- How does DeepSeek V3.2 Exp compare with the rest of the market?
- At $0.30 per million tokens, OpenRouter's own price is 65% below the typical $0.88 across the 392 text models we track.