Llama 3.1 70B Instruct vs Mistral Small 3.1 24B.
model vs model · prices as of
Llama 3.1 70B Instruct 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 $1.60, for 128k context instead of 131k.
Llama 3.1 70B Instruct
$1.60/M tokens
OpenRouter list price, nothing below it is accounted for · $0.264 per 1,000 pages
131k context · tool calling · open weights
Mistral Small 3.1 24B
$0.60/M tokens
cheapest we can explain, at NanoGPT · $0.078 per 1,000 pages
128k context · reads images · open weights
List price in (lower wins)
$0.40/M
$0.35/M
List price out (lower wins)
$0.40/M
$0.56/M
Cheapest we can explain (lower wins)
none below list
$0.60/M at NanoGPT
Standard price (lower wins)
$1.60/M
$1.61/M
Cost per 1,000 pages (lower wins)
$0.264
$0.078
Context
131k tokens
128k tokens
Open weights
yes
yes
Tool calling
yes
no
Structured output
yes
no
Reads images
no
yes
Reasoning
no
no
Released
23 Jul 2024
17 Mar 2025
Providers selling it
12
8
Price we measure against
OpenRouter
OpenRouter
Trains on your prompts (no is better)
no provider to check
not stated
Providers selling both · 3
Kilo Gateway$1.60 / $1.61
OpenRouter$1.60 / $1.61
TrustedRouter$1.69 / $1.70
Llama 3.1 70B Instruct then Mistral Small 3.1 24B, 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
- Llama 3.1 70B Instruct
Nous Portal$0.32 / $0.32 $0.40 / $0.4025% dearer ·
Frequently asked
- Which is cheaper, Llama 3.1 70B Instruct or Mistral Small 3.1 24B?
- Mistral Small 3.1 24B, at $0.60 per million tokens against $1.60 for Llama 3.1 70B Instruct, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- Llama 3.1 70B Instruct: nobody goes below OpenRouter's own price with a reason we can point at, so $1.60 is the number to beat. Mistral Small 3.1 24B: $0.60 at NanoGPT.
- Can I buy both from one provider?
- Yes. 3 providers sell both: Kilo Gateway, OpenRouter, TrustedRouter. The cheapest of them for the two together is Kilo Gateway.
- Which holds more context?
- Llama 3.1 70B Instruct, at 131k tokens against 128k.
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.