Mistral Small 3.1 24B vs Trinity Large Thinking.
model vs model · prices as of
Trinity Large Thinking takes 3 of 5 rounds against Mistral Small 3.1 24B. Mistral Small 3.1 24B counters on price: $0.60 per million tokens against $1.55, for 128k context instead of 262k.
Mistral Small 3.1 24B
$0.60/M tokens
cheapest we can explain, at NanoGPT · $0.078 per 1,000 pages
128k context · tool calling · reads images · open weights
Trinity Large Thinking
$1.55/M tokens
Arcee AI list price, nothing below it is accounted for · $0.198 per 1,000 pages
262k context · tool calling · open weights
List price in (lower wins)
$0.35/M
$0.25/M
List price out (lower wins)
$0.56/M
$0.80/M
Cheapest we can explain (lower wins)
$0.60/M at NanoGPT
none below list
Standard price (lower wins)
$1.61/M
$1.55/M
Cost per 1,000 pages (lower wins)
$0.078
$0.198
Context
128k tokens
262k tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
no
no
Reads images
yes
no
Reasoning
no
yes
Released
17 Mar 2025
1 Apr 2026
Providers selling it
9
8
Price we measure against
OpenRouter
the maker's own
Trains on your prompts (no is better)
not stated
no provider to check
Providers selling both · 5
NanoGPT$0.60 / $1.65
Kilo Gateway$1.61 / $1.55
Nous Portal$1.61 / $1.55
OpenRouter$1.61 / $1.55
TrustedRouter$1.70 / $1.64
Mistral Small 3.1 24B then Trinity Large Thinking, 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
- Mistral Small 3.1 24B
Featherless$0.70 / $1.16 $0.87 / $1.6129% dearer · - Trinity Large Thinking
Nous Portal$0.20 / $0.64 $0.25 / $0.8025% dearer ·
Frequently asked
- Which is cheaper, Mistral Small 3.1 24B or Trinity Large Thinking?
- Mistral Small 3.1 24B, at $0.60 per million tokens against $1.55 for Trinity Large Thinking, three parts input to one part output, read on 21 Sept 2026.
- Where is each one cheapest?
- Mistral Small 3.1 24B: $0.60 at NanoGPT. Trinity Large Thinking: nobody goes below the maker's own price with a reason we can point at, so $1.55 is the number to beat.
- Can I buy both from one provider?
- Yes. 5 providers sell both: NanoGPT, Kilo Gateway, Nous Portal, OpenRouter, TrustedRouter. The cheapest of them for the two together is NanoGPT.
- Which holds more context?
- Trinity Large Thinking, at 262k tokens against 128k.
Prices exclude tax and are per million tokens, read 21 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.