BroadRouter

Mistral Small 3.2 vs Gemma 3 27B API pricing

Updated

Mistral Small 3.2: USD 0.075 input, USD 0.20 output per 1M tokens (DeepInfra). Gemma 3 27B: USD 0.08 input, USD 0.16 output per 1M tokens (DeepInfra). At 3 input tokens per output token, Mistral Small 3.2 costs 6.3% more than Gemma 3 27B (USD 0.1062 vs USD 0.10 per 1M).

Mistral Small 3.2 and Gemma 3 27B are often compared as alternatives. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do Mistral Small 3.2 and Gemma 3 27B differ on price?

Mistral Small 3.2 and Gemma 3 27B prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Mistral Small 3.2 and Gemma 3 27B API prices compared
PriceMistral Small 3.2Gemma 3 27B
Model pageMistral Small 3.2 24B Instruct
Mistral AI · 4 providers
Gemma 3 27B
Google · 6 providers
Cheapest standard price, blended 3:1USD 0.1062
USD 0.075 in / USD 0.20 out at DeepInfra
DeepInfra page checked 2026-11-14
USD 0.10 lower
USD 0.08 in / USD 0.16 out at DeepInfra
DeepInfra page checked 2026-11-14
Cheapest inputUSD 0.075 lower
DeepInfra source
USD 0.08
DeepInfra source
Cheapest cached inputUSD 0.05
Parasail source
USD 0.04 lower
Parasail source
Cheapest outputUSD 0.20
DeepInfra source
USD 0.16 lower
DeepInfra source
Maker's own APIMistral AI publishes no paid standard price on its own API that we found.Google publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.091875 / USD 0.275
input / output, 4 prices
USD 0.1095 / USD 0.25
input / output, 6 prices
Context window256,000 tokens, largest stated; from 32,768 at some providers198,000 tokens, largest stated; from 32,768 at some providers
Providers with a standard price46

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do Mistral Small 3.2 and Gemma 3 27B cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Mistral Small 3.2 and Gemma 3 27B
WorkloadMistral Small 3.2Gemma 3 27BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 10.35
DeepInfra
USD 10.08
DeepInfra
USD 0.27
Gemma 3 27B lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 21.00
DeepInfra
USD 21.60
DeepInfra
USD 0.6
Mistral Small 3.2 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 127.80
Parasail
USD 123.30
Parasail
USD 4.50
Gemma 3 27B lower

The cheaper model depends on the workload: Gemma 3 27B for Support chatbot, Mistral Small 3.2 for RAG over documents, Gemma 3 27B for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on Coding agent (one developer): the dearer model costs 3.6% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

The cheaper model changes with the mix: below 8 input tokens per output token, Gemma 3 27B is cheaper; above 8, Mistral Small 3.2 is cheaper. At the site's 3:1 blend, Gemma 3 27B is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Price per 1M tokens of Mistral Small 3.2 and Gemma 3 27B at different input:output mixes
Input : output tokensMistral Small 3.2Gemma 3 27B
1 : 3 (long answers)USD 0.1688
DeepInfra
USD 0.14 lower
DeepInfra
1 : 1USD 0.1375
DeepInfra
USD 0.12 lower
DeepInfra
3 : 1 (the site’s blend)USD 0.1062
DeepInfra
USD 0.10 lower
DeepInfra
10 : 1 (retrieval, long prompts)USD 0.08636 lower
DeepInfra
USD 0.08727
DeepInfra
30 : 1 (agents, big contexts)USD 0.07903 lower
DeepInfra
USD 0.08258
DeepInfra

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Mistral Small 3.2 and Gemma 3 27B cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Mistral Small 3.2 is not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: Mistral Small 3.2 vs Mistral Small 3.1 24B · Gemma 4 31B vs Gemma 3 27B · Gemma 3 27B vs Gemma 3 12B · every Mistral Small 3.2 comparison · every Gemma 3 27B comparison · all 662 price comparisons

Questions

Is Mistral Small 3.2 cheaper than Gemma 3 27B?

No. On a blend of 3 input tokens to 1 output token, Gemma 3 27B costs USD 0.10 per 1M tokens and Mistral Small 3.2 USD 0.1062, at each model's cheapest standard price. For input alone, Mistral Small 3.2 is cheaper (USD 0.075 against USD 0.08 per 1M); for output alone, Gemma 3 27B is (USD 0.16 against USD 0.20). This compares price only, not quality.

What do Mistral Small 3.2 and Gemma 3 27B cost per 1M tokens?

Mistral Small 3.2: from USD 0.075 input and USD 0.20 output at DeepInfra; median of 4 standard prices USD 0.091875 / USD 0.275. Gemma 3 27B: from USD 0.08 input and USD 0.16 output at DeepInfra; median of 6 standard prices USD 0.1095 / USD 0.25. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Mistral Small 3.2 and Gemma 3 27B?

4 providers have a standard price for both: DeepInfra (USD 0.1062 and USD 0.10 at 3:1), Venice (USD 0.1328 and USD 0.14 at 3:1), Parasail (USD 0.1425 and USD 0.1725 at 3:1), Featherless (USD 0.2632 and USD 0.15 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.1062 and USD 0.10.

Which is cheaper for a coding agent or a chatbot, Mistral Small 3.2 or Gemma 3 27B?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 127.80 a month on Mistral Small 3.2 (Parasail) against USD 123.30 on Gemma 3 27B (Parasail), a difference of USD 4.50. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 10.35 a month on Mistral Small 3.2 (DeepInfra) against USD 10.08 on Gemma 3 27B (DeepInfra), a difference of USD 0.27. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Mistral Small 3.2 and Gemma 3 27B change?

The cheaper model changes with the mix: below 8 input tokens per output token, Gemma 3 27B is cheaper; above 8, Mistral Small 3.2 is cheaper. At the site's 3:1 blend, Gemma 3 27B is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Do Mistral Small 3.2 and Gemma 3 27B have cached input pricing?

Mistral Small 3.2 from USD 0.05 per 1M cached input tokens (Parasail; 1 of 4 standard prices list a discount). Gemma 3 27B from USD 0.04 per 1M cached input tokens (Parasail; 2 of 6 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Mistral Small 3.2 or Gemma 3 27B?

Mistral Small 3.2: up to 256,000 tokens, against 198,000 for Gemma 3 27B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity