DeepSeek V4.1 Flash vs MiniMax-M3.
model vs model · prices as of
DeepSeek V4.1 Flash takes 1 of 5 rounds against MiniMax-M3. It is also the cheaper of the two to run, at $0.70 per million tokens against $1.58.
DeepSeekwins 1 roundsDeepSeek V4.1 Flash
$0.70/M tokens
cheapest we can explain, at AMD · $0.101 per 1,000 pages
1M context · tool calling · reads images · open weights
MiniMaxMiniMax-M3
$1.58/M tokens
cheapest we can explain, at Empirio Labs · $0.189 per 1,000 pages
1M context · tool calling · reads images · open weights
List price in (lower wins)
$0.30/M
$0.30/M
List price out (lower wins)
$1.20/M
$1.20/M
Cheapest we can explain (lower wins)
$0.70/M at AMD
$1.58/M at Empirio Labs
Standard price (lower wins)
$2.10/M
$2.10/M
Cost per 1,000 pages (lower wins)
$0.101
$0.189
Context
1M tokens
1M tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
yes
not stated
Reads images
yes
yes
Reasoning
yes
yes
Released
10 Sept 2026
1 Jun 2026
Providers selling it
58
57
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 35
Nous Portal$1.04 / $1.65
NanoGPT$0.78 / $2.10
DeepInfra$1.20 / $1.94
ClinePass$1.05 / $2.10
LLM Gateway$1.05 / $2.10
Merge Gateway$1.05 / $2.10
OpenCode Go$1.05 / $2.10
FastRouter$1.20 / $2.10
DeepSeek V4.1 Flash then MiniMax-M3, per million tokens · showing the 8 cheapest of 35
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- DeepSeek V4.1 FlashDeepSeek$0.15 / $0.60 $0.30 / $1.20100% dearer ·
- DeepSeek V4.1 Flash
io.net Intelligence$0.31 / $1.24 $0.31 / $1.221.0% cheaper · - DeepSeek V4.1 FlashDeepSeekDeepSeek's list price, in and out per million tokens$0.15 / $0.60 $0.30 / $1.20100% dearer ·
- DeepSeek V4.1 Flash
Morph$0.24 / $0.96 $0.15 / $0.5938% cheaper · - DeepSeek V4.1 FlashNous Portal$0.15 / $0.60 $0.15 / $0.591.0% cheaper ·
- DeepSeek V4.1 Flash
Novita$0.30 / $1.20 $0.28 / $1.145% cheaper · - DeepSeek V4.1 Flash
OpenRouter$0.15 / $0.60 $0.30 / $1.20100% dearer · - DeepSeek V4.1 Flash
Requesty$0.15 / $0.60 $0.50 / $1.50186% dearer · - DeepSeek V4.1 Flash
Wafer$0.30 / $1.20 $0.20 / $0.6043% cheaper · - MiniMax-M3
Cortecs$0.41 / $2.05 $0.41 / $2.040.5% cheaper · - MiniMax-M3Requesty$0.40 / $2 $0.30 / $1.2034% cheaper ·
- DeepSeek V4.1 Flash
Charm Hyper$0.33 / $1.31 $0.30 / $1.208% cheaper · - DeepSeek V4.1 Flash
Eden AI$0.50 / $1.50 $0.30 / $1.2030% cheaper · - DeepSeek V4.1 Flash
Vercel AI Gateway$0.15 / $0.60 $0.30 / $1.20100% dearer · - DeepSeek V4.1 Flash
GMI Cloud$0.30 / $1.20 $0.28 / $1.145% cheaper · - DeepSeek V4.1 Flash
Kenari$0.35 / $0.70 $0.01 / $0.0396% cheaper · - DeepSeek V4.1 Flash
TrustedRouter$0.16 / $0.63 $0.04 / $0.0881% cheaper · - MiniMax-M3Nous Portal$0.18 / $0.77 $0.23 / $0.9625% dearer ·
- DeepSeek V4.1 FlashDeepInfra$0.30 / $1.20 $0.20 / $0.6043% cheaper ·
Frequently asked
- Which is cheaper, DeepSeek V4.1 Flash or MiniMax-M3?
- DeepSeek V4.1 Flash, at $0.70 per million tokens against $1.58 for MiniMax-M3, three parts input to one part output, read on 18 Sept 2026.
- Where is each one cheapest?
- DeepSeek V4.1 Flash: $0.70 at AMD. MiniMax-M3: $1.58 at Empirio Labs.
- Can I buy both from one provider?
- Yes. 35 providers sell both: Nous Portal, NanoGPT, DeepInfra, ClinePass, LLM Gateway, Merge Gateway, and more. The cheapest of them for the two together is Nous Portal.
- Which holds more context?
- Both hold 1M tokens in one call.
Prices exclude tax and are per million tokens, read 18 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.