DeepSeek V3.1 vs MiniMax-01.
model vs model · prices as of
DeepSeek V3.1 takes 3 of 5 rounds against MiniMax-01. It is also the cheaper of the two to run, at $1.40 per million tokens against $1.54.
DeepSeekwins 3 roundsDeepSeek V3.1
$1.40/M tokens
cheapest we can explain, at TensorX · $0.168 per 1,000 pages
164k context · tool calling · open weights
MiniMaxMiniMax-01
$1.54/M tokens
cheapest we can explain, at NanoGPT · $0.151 per 1,000 pages
1M context · reads images · open weights
List price in (lower wins)
$0.25/M
$0.20/M
List price out (lower wins)
$0.95/M
$1.10/M
Cheapest we can explain (lower wins)
$1.40/M at TensorX
$1.54/M at NanoGPT
Standard price (lower wins)
$1.70/M
$1.70/M
Cost per 1,000 pages (lower wins)
$0.168
$0.151
Context
164k tokens
1M tokens
Open weights
yes
yes
Tool calling
yes
no
Structured output
yes
no
Reads images
no
yes
Reasoning
yes
no
Released
21 Aug 2025
15 Jan 2025
Providers selling it
12
4
Price we measure against
OpenRouter
the maker's own
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 2
OpenRouter$1.70 / $1.70
Kilo Gateway$1.81 / $1.70
DeepSeek V3.1 then MiniMax-01, per million tokens
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- DeepSeek V3.1
Nous Portal$0.20 / $0.76 $0.25 / $0.9525% dearer ·
Frequently asked
- Which is cheaper, DeepSeek V3.1 or MiniMax-01?
- DeepSeek V3.1, at $1.40 per million tokens against $1.54 for MiniMax-01, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- DeepSeek V3.1: $1.40 at TensorX. MiniMax-01: $1.54 at NanoGPT.
- Can I buy both from one provider?
- Yes. 2 providers sell both: OpenRouter, Kilo Gateway. The cheapest of them for the two together is OpenRouter.
- Which holds more context?
- MiniMax-01, at 1M tokens against 164k.
Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.