Devstral Small 2505 vs Llama 3.3 70B Instruct
Prices checked
Devstral Small 2505 takes 3 of 5 rounds against Llama 3.3 70B Instruct. It is also the cheaper of the two to run, at $0.06 per million tokens against $0.10.
Mistral AIWins 3 roundsDevstral Small 2505
128k context · tool calling · open weights
$0.06/M tokensCheapest price, at NanoGPT · 4¢ per 1,000 pages
MetaLlama 3.3 70B Instruct
128k context · tool calling · open weights
$0.10/M tokensCheapest price, at NanoGPT · 4.4¢ per 1,000 pages
Maker's price in (lower wins)
$0.10/M
$0.10/M
Maker's price out (lower wins)
$0.30/M
$0.32/M
Cheapest price (lower wins)
$0.06/M at NanoGPT
$0.10/M at NanoGPT
Maker's price, blended (lower wins)
$0.15/M
$0.16/M
Cost per 1,000 pages (lower wins)
4¢
4.4¢
Context
128k tokens
128k tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
not published
not published
Reads images
no
no
Reasoning
no
no
Released
7 May 2025
6 Dec 2024
Providers selling it
10
48
Price we measure against
the maker's own
OpenRouter
Trains on your prompts (no is better)
not published
not published
Providers selling both · 6
NanoGPT$0.06 / $0.10
Eden AI$0.15 / $0.15
TrustedRouter$0.16 / $0.16
Requesty$0.17 / $0.17
Merge Gateway$0.15 / $0.29
io.net Intelligence$0.09 / $0.67
Devstral Small 2505, then Llama 3.3 70B Instruct, per million tokens.
Go further
Add a third or fourth model, or change the weighting, in the tool.
What moved this week
- Eden AI · 0.3% cheaper · $1.23 / $1.23 $1.24 / $1.24
- Eden AI · 44% dearer · $0.22 / $0.50 $0.14 / $0.40
- $0.10 / $0.32 $0.59 / $0.79
OpenRouter · 76% cheaper · $0.10 / $0.32 $0.59 / $0.79
Frequently asked
- Which is cheaper, Devstral Small 2505 or Llama 3.3 70B Instruct?
- Devstral Small 2505, at $0.06 per million tokens against $0.10 for Llama 3.3 70B Instruct, blended 3 in : 1 out, read on 21 Oct 2026.
- Where is each one cheapest?
- Devstral Small 2505: $0.06 at NanoGPT. Llama 3.3 70B Instruct: $0.10 at NanoGPT.
- Can I buy both from one provider?
- Yes. 6 providers sell both: NanoGPT, Eden AI, TrustedRouter, Requesty, Merge Gateway, io.net Intelligence. The cheapest of them for the two together is NanoGPT.
- Which holds more context?
- Both hold 128k tokens in one call.
Prices exclude tax, read 21 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