BroadRouter

Mistral Small 3.2 vs GPT OSS Safeguard 20B API pricing

Updated

Mistral Small 3.2: USD 0.075 input, USD 0.20 output per 1M tokens (DeepInfra). GPT OSS Safeguard 20B: USD 0.07 input, USD 0.20 output per 1M tokens (Amazon Bedrock). At 3 input tokens per output token, Mistral Small 3.2 costs 3.7% more than GPT OSS Safeguard 20B (USD 0.1062 vs USD 0.1025 per 1M).

Picked by the same-tier rule: both are in the first quarter of the indexed models by price (below USD 0.1556 per 1M tokens at 3:1) and in the same size class, small (a tier word such as Flash, Mini or Haiku, or 40B parameters or fewer). Mistral Small 3.2 is the 3rd-closest-priced model from another maker to GPT OSS Safeguard 20B in that bucket. 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 GPT OSS Safeguard 20B differ on price?

Mistral Small 3.2 and GPT OSS Safeguard 20B 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 GPT OSS Safeguard 20B API prices compared
PriceMistral Small 3.2GPT OSS Safeguard 20B
Model pageMistral Small 3.2 24B Instruct
Mistral AI · 4 providers
GPT OSS Safeguard 20B
OpenAI · 3 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 0.1025 lower
USD 0.07 in / USD 0.20 out at Amazon Bedrock
Amazon Bedrock page checked 2026-11-14
Cheapest inputUSD 0.075
DeepInfra source
USD 0.07 lower
Amazon Bedrock source
Cheapest cached inputUSD 0.05
Parasail source
USD 0.037 lower
Groq source
Cheapest outputUSD 0.20 tie
DeepInfra source
USD 0.20 tie
Amazon Bedrock source
Maker's own APIMistral AI publishes no paid standard price on its own API that we found.OpenAI 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 0.075 / USD 0.30
input / output, 3 prices
Context window256,000 tokens, largest stated; from 32,768 at some providers131,072 tokens, largest stated; from 32,768 at some providers
Providers with a standard price43

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 GPT OSS Safeguard 20B 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 GPT OSS Safeguard 20B
WorkloadMistral Small 3.2GPT OSS Safeguard 20BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 10.35
DeepInfra
USD 9.90
Amazon Bedrock
USD 0.45
GPT OSS Safeguard 20B lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 21.00
DeepInfra
USD 19.76
Groq
USD 1.24
GPT OSS Safeguard 20B 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 103.86
Groq
USD 23.94
GPT OSS Safeguard 20B lower

GPT OSS Safeguard 20B is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 23% more than the cheaper one.

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

GPT OSS Safeguard 20B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Mistral Small 3.2's, so the input:output ratio never changes the answer. On output price alone they tie.

Price per 1M tokens of Mistral Small 3.2 and GPT OSS Safeguard 20B at different input:output mixes
Input : output tokensMistral Small 3.2GPT OSS Safeguard 20B
1 : 3 (long answers)USD 0.1688
DeepInfra
USD 0.1675 lower
Amazon Bedrock
1 : 1USD 0.1375
DeepInfra
USD 0.135 lower
Amazon Bedrock
3 : 1 (the site’s blend)USD 0.1062
DeepInfra
USD 0.1025 lower
Amazon Bedrock
10 : 1 (retrieval, long prompts)USD 0.08636
DeepInfra
USD 0.08182 lower
Amazon Bedrock
30 : 1 (agents, big contexts)USD 0.07903
DeepInfra
USD 0.07419 lower
Amazon Bedrock

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 GPT OSS Safeguard 20B 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 Gemma 3 27B · Mistral Small 3.2 vs Mistral Small 3.1 24B · every Mistral Small 3.2 comparison · every GPT OSS Safeguard 20B comparison · all 662 price comparisons

Questions

Is Mistral Small 3.2 cheaper than GPT OSS Safeguard 20B?

No. On a blend of 3 input tokens to 1 output token, GPT OSS Safeguard 20B costs USD 0.1025 per 1M tokens and Mistral Small 3.2 USD 0.1062, at each model's cheapest standard price. For input alone, GPT OSS Safeguard 20B is cheaper (USD 0.07 against USD 0.075 per 1M); for output alone, both start at USD 0.20. This compares price only, not quality.

What do Mistral Small 3.2 and GPT OSS Safeguard 20B 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. GPT OSS Safeguard 20B: from USD 0.07 input and USD 0.20 output at Amazon Bedrock; median of 3 standard prices USD 0.075 / USD 0.30. 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 GPT OSS Safeguard 20B?

1 provider has a standard price for both: Featherless (USD 0.2632 and USD 0.1312 at 3:1). Buying each model from its own cheapest provider costs USD 0.1062 and USD 0.1025.

Which is cheaper for a coding agent or a chatbot, Mistral Small 3.2 or GPT OSS Safeguard 20B?

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 103.86 on GPT OSS Safeguard 20B (Groq), a difference of USD 23.94. 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 9.90 on GPT OSS Safeguard 20B (Amazon Bedrock), a difference of USD 0.45. 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 GPT OSS Safeguard 20B change?

GPT OSS Safeguard 20B is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Mistral Small 3.2's, so the input:output ratio never changes the answer. On output price alone they tie.

Do Mistral Small 3.2 and GPT OSS Safeguard 20B 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). GPT OSS Safeguard 20B from USD 0.037 per 1M cached input tokens (Groq; 1 of 3 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 GPT OSS Safeguard 20B?

Mistral Small 3.2: up to 256,000 tokens, against 131,072 for GPT OSS Safeguard 20B, 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