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).
How do Mistral Small 3.2 and GPT OSS Safeguard 20B differ on price?
- Cheapest input price: GPT OSS Safeguard 20B USD 0.07 against USD 0.075 per 1M tokens, so Mistral Small 3.2 costs 1.07× as much (7% more).
- Cheapest output price: both USD 0.20 per 1M tokens.
- Among the 201 indexed models, Mistral Small 3.2 ranks 24th cheapest and GPT OSS Safeguard 20B 23rd on the 3:1 blend.
- No input:output mix changes the answer: GPT OSS Safeguard 20B is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Mistral Small 3.2 at 1 standard price of 4, from USD 0.05 (Parasail, 44% below that provider's input price); GPT OSS Safeguard 20B at 1 standard price of 3, from USD 0.037 (Groq, 51% below that provider's input price).
- Mistral Small 3.2 states up to 256,000 tokens of context, 1.95× the 131,072 of GPT OSS Safeguard 20B.
- Mistral Small 3.2 has 4 providers with a standard price, 1 more than GPT OSS Safeguard 20B; 1 provider sells both (Featherless).
- On one account, Featherless charges USD 0.2632 for Mistral Small 3.2 (2.5× its cheapest price) and USD 0.1312 for GPT OSS Safeguard 20B (1.28× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Mistral Small 3.2: its dearest standard price is 2.5× its cheapest, against 1.28× for GPT OSS Safeguard 20B.
- For the one-developer coding agent preset, the gap is USD 287.28 a year in GPT OSS Safeguard 20B's favour (Mistral Small 3.2 USD 127.80 a month, GPT OSS Safeguard 20B USD 103.86).
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.
| Price | Mistral Small 3.2 | GPT OSS Safeguard 20B |
|---|---|---|
| Model page | Mistral Small 3.2 24B Instruct Mistral AI · 4 providers | GPT OSS Safeguard 20B OpenAI · 3 providers |
| Cheapest standard price, blended 3:1 | USD 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 input | USD 0.075 DeepInfra source | USD 0.07 lower Amazon Bedrock source |
| Cheapest cached input | USD 0.05 Parasail source | USD 0.037 lower Groq source |
| Cheapest output | USD 0.20 tie DeepInfra source | USD 0.20 tie Amazon Bedrock source |
| Maker's own API | Mistral 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 price | USD 0.091875 / USD 0.275 input / output, 4 prices | USD 0.075 / USD 0.30 input / output, 3 prices |
| Context window | 256,000 tokens, largest stated; from 32,768 at some providers | 131,072 tokens, largest stated; from 32,768 at some providers |
| Providers with a standard price | 4 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
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).
| Workload | Mistral Small 3.2 | GPT OSS Safeguard 20B | Difference |
|---|---|---|---|
| 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.
| Input : output tokens | Mistral Small 3.2 | GPT OSS Safeguard 20B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.1688 DeepInfra | USD 0.1675 lower Amazon Bedrock |
| 1 : 1 | USD 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
- Mistral Small 3.2 24B Instruct API pricing: all 4 providers and other tiers.
- GPT OSS Safeguard 20B API pricing: all 3 providers and other tiers.
- Cost calculator with Mistral Small 3.2 and GPT OSS Safeguard 20B preloaded
- Token counter
- gpt-oss token counter
- Prompt caching calculator
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.