Llama 3.1 8B Instruct vs Mistral Small 3
Prices checked
Llama 3.1 8B Instruct takes 2 of 5 rounds against Mistral Small 3. It is also the cheaper of the two to run, at $0.02 per million tokens against $0.06.
MetaWins 2 roundsLlama 3.1 8B Instruct
131k context · tool calling · open weights
$0.02/M tokensCheapest price, at Helicone · 1.4¢ per 1,000 pages
Mistral AIMistral Small 3
33k context · open weights
$0.06/M tokensOpenRouter's own price · 3.5¢ per 1,000 pages
Maker's price in (lower wins)
$0.05/M
$0.05/M
Maker's price out (lower wins)
$0.08/M
$0.08/M
Cheapest price (lower wins)
$0.02/M at Helicone
none below the maker
Maker's price, blended (lower wins)
$0.06/M
$0.06/M
Cost per 1,000 pages (lower wins)
1.4¢
3.5¢
Context
131k tokens
33k tokens
Open weights
yes
yes
Tool calling
yes
no
Structured output
yes
yes
Reads images
no
no
Reasoning
no
no
Released
23 Jul 2024
30 Jan 2025
Providers selling it
29
11
Price we measure against
OpenRouter
OpenRouter
Trains on your prompts (no is better)
not published
no provider to check
Providers selling both · 7
DeepInfra$0.03 / $0.06
Kilo Gateway$0.03 / $0.06
TrustedRouter$0.03 / $0.06
OpenRouter$0.06 / $0.06
Eden AI$0.03 / $0.17
NanoGPT$0.02 / $0.17
Together AI$0.18 / $0.15
Llama 3.1 8B Instruct, then Mistral Small 3, per million tokens.
Go further
Add a third or fourth model, or change the weighting, in the tool.
What moved this week
Nous Portal · 130% dearer · 5¢ / 8¢ 2¢ / 4¢- Eden AI · 0.4% dearer · $0.11 / $0.34 $0.11 / $0.33
- Eden AI · 445% dearer · $0.15 / $0.15 2¢ / 5¢
Frequently asked
- Which is cheaper, Llama 3.1 8B Instruct or Mistral Small 3?
- Llama 3.1 8B Instruct, at $0.02 per million tokens against $0.06 for Mistral Small 3, blended 3 in : 1 out, read on 31 Oct 2026.
- Where is each one cheapest?
- Llama 3.1 8B Instruct: $0.02 at Helicone. Mistral Small 3: nobody sells it below OpenRouter's own price with a stated reason, so $0.06 is the number to beat.
- Can I buy both from one provider?
- Yes. 7 providers sell both: DeepInfra, Kilo Gateway, TrustedRouter, OpenRouter, Eden AI, NanoGPT, and more. The cheapest of them for the two together is DeepInfra.
- Which holds more context?
- Llama 3.1 8B Instruct, at 131k tokens against 33k.
Prices exclude tax, read 31 Oct 2026 from each provider's own catalog. They are per M tokens, blended 3 in : 1 out, and a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.
Related comparisons