Mistral Small 3.2 vs Qwen3.5 9B API pricing
Updated
Mistral Small 3.2: USD 0.075 input, USD 0.20 output per 1M tokens (DeepInfra). Qwen3.5 9B: USD 0.10 input, USD 0.15 output per 1M tokens (DeepInfra and 1 other). At 3 input tokens per output token, Qwen3.5 9B costs 5.9% more than Mistral Small 3.2 (USD 0.1125 vs USD 0.1062 per 1M).
How do Mistral Small 3.2 and Qwen3.5 9B differ on price?
- Cheapest input price: Mistral Small 3.2 USD 0.075 against USD 0.10 per 1M tokens, so Qwen3.5 9B costs 1.33× as much (33% more).
- Cheapest output price: Qwen3.5 9B USD 0.15 against USD 0.20 per 1M tokens, so Mistral Small 3.2 costs 1.33× as much (33% more).
- Among the 201 indexed models, Mistral Small 3.2 ranks 24th cheapest and Qwen3.5 9B 25th on the 3:1 blend.
- The cheaper model changes at 2 input tokens per output token.
- Only Mistral Small 3.2 lists a cached-input discount: Mistral Small 3.2 at 1 standard price of 4, from USD 0.05 (Parasail, 44% below that provider's input price). Qwen3.5 9B's cached tokens bill at the input price.
- Qwen3.5 9B states up to 262,144 tokens of context and Mistral Small 3.2 256,000, within 10% of each other.
- Both have 4 providers with a standard price; 2 providers sell both (DeepInfra and Featherless).
- On one account, DeepInfra charges USD 0.1062 for Mistral Small 3.2 (its cheapest price) and USD 0.1125 for Qwen3.5 9B (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 1.69× for Qwen3.5 9B.
- For the one-developer coding agent preset, the gap is USD 788.40 a year in Mistral Small 3.2's favour (Mistral Small 3.2 USD 127.80 a month, Qwen3.5 9B USD 193.50).
Mistral Small 3.2 and Qwen3.5 9B 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 | Qwen3.5 9B |
|---|---|---|
| Model page | Mistral Small 3.2 24B Instruct Mistral AI · 4 providers | Qwen3.5 9B Qwen · 4 providers |
| Cheapest standard price, blended 3:1 | USD 0.1062 lower USD 0.075 in / USD 0.20 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.1125 USD 0.10 in / USD 0.15 out at DeepInfra and 1 other DeepInfra page checked 2026-11-14 |
| Cheapest input | USD 0.075 lower DeepInfra source | USD 0.10 DeepInfra source |
| Cheapest cached input | USD 0.05 Parasail source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.20 DeepInfra source | USD 0.15 lower DeepInfra source |
| Maker's own API | Mistral AI publishes no paid standard price on its own API that we found. | Qwen 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 0.135 / USD 0.20 input / output, 4 prices |
| Context window | 256,000 tokens, largest stated; from 32,768 at some providers | 262,144 tokens, largest stated; from 32,768 at some providers |
| Providers with a standard price | 4 | 4 |
- 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 Qwen3.5 9B 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 | Qwen3.5 9B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 10.35 DeepInfra | USD 11.70 DeepInfra | USD 1.35 Mistral Small 3.2 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 21.00 DeepInfra | USD 26.25 DeepInfra | USD 5.25 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 193.50 DeepInfra | USD 65.70 Mistral Small 3.2 lower |
Mistral Small 3.2 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 51% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 2 input tokens per output token, Qwen3.5 9B is cheaper; above 2, Mistral Small 3.2 is cheaper. At the site's 3:1 blend, Mistral Small 3.2 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.
| Input : output tokens | Mistral Small 3.2 | Qwen3.5 9B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.1688 DeepInfra | USD 0.1375 lower DeepInfra |
| 1 : 1 | USD 0.1375 DeepInfra | USD 0.125 lower DeepInfra |
| 3 : 1 (the site’s blend) | USD 0.1062 lower DeepInfra | USD 0.1125 DeepInfra |
| 10 : 1 (retrieval, long prompts) | USD 0.08636 lower DeepInfra | USD 0.1045 DeepInfra |
| 30 : 1 (agents, big contexts) | USD 0.07903 lower DeepInfra | USD 0.1016 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 Qwen3.5 9B 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.
- Qwen3.5 9B API pricing: all 4 providers and other tiers.
- Cost calculator with Mistral Small 3.2 and Qwen3.5 9B preloaded
- Token counter
- Qwen 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 · Qwen3.5 9B vs Qwen3-8B · Qwen3.5 27B vs Qwen3.5 9B · every Mistral Small 3.2 comparison · every Qwen3.5 9B comparison · all 662 price comparisons
Questions
Is Mistral Small 3.2 cheaper than Qwen3.5 9B?
Yes. On a blend of 3 input tokens to 1 output token, Mistral Small 3.2 costs USD 0.1062 per 1M tokens and Qwen3.5 9B USD 0.1125, at each model's cheapest standard price. For input alone, Mistral Small 3.2 is cheaper (USD 0.075 against USD 0.10 per 1M); for output alone, Qwen3.5 9B is (USD 0.15 against USD 0.20). This compares price only, not quality.
What do Mistral Small 3.2 and Qwen3.5 9B 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. Qwen3.5 9B: from USD 0.10 input and USD 0.15 output at DeepInfra and 1 other; median of 4 standard prices USD 0.135 / USD 0.20. 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 Qwen3.5 9B?
2 providers have a standard price for both: DeepInfra (USD 0.1062 and USD 0.1125 at 3:1), Featherless (USD 0.2632 and USD 0.19 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.1062 and USD 0.1125.
Which is cheaper for a coding agent or a chatbot, Mistral Small 3.2 or Qwen3.5 9B?
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 193.50 on Qwen3.5 9B (DeepInfra), a difference of USD 65.70. 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 11.70 on Qwen3.5 9B (DeepInfra), a difference of USD 1.35. 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 Qwen3.5 9B change?
The cheaper model changes with the mix: below 2 input tokens per output token, Qwen3.5 9B is cheaper; above 2, Mistral Small 3.2 is cheaper. At the site's 3:1 blend, Mistral Small 3.2 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 Qwen3.5 9B 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). Qwen3.5 9B: no standard price lists a cached-input 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 Qwen3.5 9B?
Qwen3.5 9B: up to 262,144 tokens, against 256,000 for Mistral Small 3.2, 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.