Ministral 3B (latest) vs text-embedding-3-small.

model vs model · prices as of

text-embedding-3-small takes 3 of 5 rounds against Ministral 3B (latest). It is also the cheaper of the two to run, at $0.06 per million tokens against $0.16.

Mistral AI

Ministral 3B (latest)

$0.16/M tokens

Mistral AI list price, nothing below it is accounted for · $0.0264 per 1,000 pages

128k context · tool calling · open weights

OpenAIwins 3 rounds

text-embedding-3-small

$0.06/M tokens

OpenAI list price, nothing below it is accounted for · $0.012 per 1,000 pages

8k context

List price in (lower wins)

$0.04/M

$0.02/M

List price out (lower wins)

$0.04/M

$0/M

Cheapest we can explain (lower wins)

none below list

none below list

Standard price (lower wins)

$0.16/M

$0.06/M

Cost per 1,000 pages (lower wins)

$0.0264

$0.012

Context

128k tokens

8k tokens

Open weights

yes

no

Tool calling

yes

no

Structured output

not stated

not stated

Reads images

no

no

Reasoning

no

no

Released

1 Oct 2024

25 Jan 2024

Providers selling it

14

9

Price we measure against

the maker's own

the maker's own

Trains on your prompts (no is better)

no provider to check

no provider to check

Providers selling both · 4

  • Azure AI Foundry$0.16 / $0.06
  • Azure Cognitive Services$0.16 / $0.06
  • LLM Gateway$0.40 / $0.06
  • Nous Portal$0.40 / $0.06

Ministral 3B (latest) then text-embedding-3-small, 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

  1. Ministral 3B (latest)Cortecs$0.12 / $0.12 $0.13 / $0.1310% dearer ·
  2. Ministral 3B (latest)Nous Portal$0.08 / $0.08 $0.10 / $0.1025% dearer ·

Frequently asked

Which is cheaper, Ministral 3B (latest) or text-embedding-3-small?
text-embedding-3-small, at $0.06 per million tokens against $0.16 for Ministral 3B (latest), three parts input to one part output, read on 16 Sept 2026.
Where is each one cheapest?
Ministral 3B (latest): nobody goes below the maker's own price with a reason we can point at, so $0.16 is the number to beat. text-embedding-3-small: nobody goes below the maker's own price with a reason we can point at, so $0.06 is the number to beat.
Can I buy both from one provider?
Yes. 4 providers sell both: Azure AI Foundry, Azure Cognitive Services, LLM Gateway, Nous Portal. The cheapest of them for the two together is Azure AI Foundry.
Which holds more context?
Ministral 3B (latest), at 128k tokens against 8k.

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.

Related head-to-headsgpt-oss-20b vs Ministral 3B (latest)Ling 3.0 Flash vs Ministral 3B (latest)Ling 3.0 Flash vs text-embedding-3-smallMorecompare any two modelsevery model we track