DeepSeek V3.1 Terminus pricing.
Prices checked
DeepSeek V3.1 Terminus costs $0.27 in and $1 out per million tokens from OpenRouter; the cheapest price is $0.36 at NanoGPT, checked .
OpenRouter's own price
OpenRouter
$0.27 in · $1 out
49% below the typical price of the 392 text models we track.
Cheapest price
NanoGPT
$0.25 in · $0.70 out
20% less than OpenRouter, and the provider says why.
Every provider selling DeepSeek V3.1 Terminus
- 1
$0.25 in · $0.70 out · 128k context here
$0.36/M tokens - 2
$0.25 in · $0.70 out · 128k context here
$0.36/M tokens - 3
$0.27 in · $0.95 out
$0.44/M tokens - 4
$0.27 in · $1 out
$0.45/M tokens - 5
$0.27 in · $1 out
$0.45/M tokens - 6
$0.27 in · $1 out · 128k context here
$0.45/M tokens - 7
$0.27 in · $1 out · 128k context here
$0.45/M tokens - 8
$0.27 in · $1 out
$0.45/M tokens - 9
$0.27 in · $1 out
$0.45/M tokens - 10
$0.27 in · $1 out
$0.45/M tokens - 11
$0.27 in · $1 out · 131k context here
$0.45/M tokens - 12
$0.27 in · $1 out
$0.45/M tokens - 13
$0.27 in · $1 out
$0.45/M tokens - 14
Qiniu
Costs more$0.58 in · $1.74 out · 128k context here
$0.87/M tokens - 15
$0.60 in · $1.79 out
$0.90/M tokens - 16
$0.60 in · $1.81 out
$0.90/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why
$0.28 in · $1 out · 131k context here
$0.46/M tokens
What it costs for your work
A month at OpenRouter's own price
A month at NanoGPT, 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.
How 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 V3.1 Terminus 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.
- Not ranked
- Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.
Similar models
Models from other labs that do what DeepSeek V3.1 Terminus does, cheapest first. Each percentage is against DeepSeek V3.1 Terminus's cheapest price, $0.36 per M tokens.
Frequently asked
- Who sells DeepSeek V3.1 Terminus cheapest?
- NanoGPT, at $0.25 in and $0.70 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 V3.1 Terminus open weights?
- Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V3.1 Terminus, which is why 15 providers sell it and why their prices differ so much.
- How much context does DeepSeek V3.1 Terminus hold?
- 163,840 tokens in one call, which is about 164k, and it can call your own functions.
- How does DeepSeek V3.1 Terminus compare with the rest of the market?
- At $0.45 per million tokens, OpenRouter's own price is 49% below the typical $0.88 across the 392 text models we track.