Mistral Small 3.2 24B Instruct API pricing
Updated
Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Mistral Small 3.2 24B Instruct is DeepInfra at USD 0.075 per 1M input tokens and USD 0.20 per 1M output tokens. The median across 4 standard prices is USD 0.091875 / USD 0.275. Each price is read from the provider's own pricing page.
Does Mistral AI sell Mistral Small 3.2 24B Instruct directly?
Mistral AI publishes no price for Mistral Small 3.2 24B Instruct on its own API that we could find, so this page compares hosts only.
Mistral Small 3.2 24B Instruct model facts
Facts from Mistral AI's model card for mistralai/Mistral-Small-3.2-24B-Instruct-2506 and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (mistralai/Mistral-Small-3.2-24B-Instruct-2506) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 11 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | Mistral AI model card metadata, checked 2026-11-16Quote“license: apache-2.0” |
| Parameters in the weight files (Hugging Face count, not the maker's figure) | About 24.0 billion (24,011,361,280) | Hugging Face model API, checked 2026-11-16Quote“"safetensors": { "total": 24011361280 }” |
| Context length | Not found on Mistral AI's model card when we read it; see the context column in the price table | checked 2026-11-16 |
| Tool calling | Yes | Mistral AI model card, checked 2026-11-16Quote“Mistral-Small-3.2-24B-Instruct-2506 is excellent at function / tool calling tasks via vLLM.” |
| First published on Hugging Face (not necessarily the release date) | 2025-06-19 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2025-06-19T17:41:13.000Z"” |
Mistral Small 3.2 24B Instruct price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.5× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepInfra cheapestmistralai/Mistral-Small-3.2-24B-Instruct-2506Notes and source quote“$0.075 in $0.20 out / 1M tokens” | USD 0.075 | not published | USD 0.20 | USD 0.1062 | 128,000 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | Venicemistral-small-3-2-24b-instructNotes and source quote“| Mistral Small 3.2 24B Instruct | `mistral-small-3-2-24b-instruct` | $0.09375 | $0.25 | — | — | Private |” | USD 0.09375 | not published | USD 0.25 | USD 0.1328 | 256,000 | FP8 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | ParasailNotes and source quote“Mistral Small 3.2 24B $0.09 $0.30 $0.05” | USD 0.09 | USD 0.05 | USD 0.30 | USD 0.1425 | not stated | not stated | Parasail page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Featherlessmistralai/Mistral-Small-3.2-24B-Instruct-2506Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). No cached price published. “PRICING: INPUT $0.2168 / OUTPUT $0.4025” | USD 0.2168 | not published | USD 0.4025 | USD 0.2632 | 32,768 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| — | DeepInfra flex / spotmistralai/Mistral-Small-3.2-24B-Instruct-2506Notes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.06 $0.16” | USD 0.06 | not published | USD 0.16 | USD 0.085 | 128,000 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra prioritymistralai/Mistral-Small-3.2-24B-Instruct-2506Notes and source quotePriority service tier (1.5× standard). “Priority (1.5×) $0.1125 $0.30” | USD 0.1125 | not published | USD 0.30 | USD 0.1594 | 128,000 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (flex / spot and priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Mistral Small 3.2 24B Instruct cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| DeepInfra | USD 10.35 | USD 21.00 | USD 153.00 |
| Venice | USD 12.94 | USD 26.25 | USD 191.25 |
| Parasail | USD 11.34 | USD 23.22 | USD 127.80 |
| Featherless | USD 26.76 | USD 58.07 | exceeds context |
For the support chatbot, the cheapest price (DeepInfra, USD 10.35 a month) saves USD 1.79 against the median (USD 12.14). For the coding agent the gap is USD 44.33 a month (26% lower). The winner changes with the workload: Parasail wins the cache-heavy agent, DeepInfra the chatbot.
Which Mistral Small 3.2 24B Instruct provider is cheapest for your traffic?
DeepInfra has the lowest input price (USD 0.075) and the lowest output price (USD 0.20), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| DeepInfra (no cache price) | USD 0.1062 cheapest | USD 0.1062 cheapest | USD 0.1062 cheapest |
| Venice (no cache price) | USD 0.1328 | USD 0.1328 | USD 0.1328 |
| Parasail | USD 0.1425 | USD 0.1275 | USD 0.1155 |
| Featherless (no cache price) | USD 0.2632 | USD 0.2632 | USD 0.2632 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
1 of 4 providers publishes a cached-input price below the input price: Parasail (44% off). DeepInfra, Venice and Featherless publish none, so cached tokens there bill at the input price.
Context windows differ: 256,000 tokens at Venice; 128,000 tokens at DeepInfra; 32,768 tokens at Featherless. Parasail does not state one. The cheapest row is not always the one that fits a long prompt.
Estimate your own bill
- LLM API cost calculator with Mistral Small 3.2 24B Instruct preloaded: your traffic and cache rate, against any of 429 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Mistral Small 3.2 24B Instruct compare with other Mistral AI models?
The Mistral AI models whose cheapest standard price is closest to Mistral Small 3.2 24B Instruct's (USD 0.1062 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Ministral 3 3B | USD 0.10 | USD 0.10 | 262,144 | 2 |
| Ministral 3 8B | USD 0.15 | USD 0.15 | 262,144 | 2 |
| Mistral Small 3.1 24B Instruct | USD 0.10 | USD 0.30 | 32,768 | 4 |
| Mistral-Small-24B-Instruct-2501 | USD 0.05 | USD 0.08 | 32,768 | 2 |
| Ministral 3 14B | USD 0.20 | USD 0.20 | 262,144 | 3 |
| Mistral-Nemo-Instruct-2407 | USD 0.029 | USD 0.03 | 131,072 | 2 |
Priced closest from other makers: GPT OSS Safeguard 20B (OpenAI, USD 0.1025) · DeepSeek V4 Flash (DeepSeek, USD 0.1125) · Qwen3.5 9B (Qwen, USD 0.1125).
Compare Mistral Small 3.2 24B Instruct with
- Mistral Small 3.2 vs Gemma 3 27B: API price side by side
- Mistral Small 3.2 vs Mistral Small 3.1 24B: API price side by side
Also compared: vs Gemma 3 27B · vs Mistral Small 3.1 24B Instruct.
Every Mistral Small 3.2 24B Instruct price comparison · All model-vs-model price comparisons
All 429 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Mistral Small 3.2 24B Instruct API cost per token?
From USD 0.075 per 1M input tokens (USD 0.000000075 per token) and USD 0.20 per 1M output tokens (USD 0.0000002 per token) at the lowest standard prices we found. The median of 4 standard prices is USD 0.091875 input and USD 0.275 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Mistral Small 3.2 24B Instruct?
Among the 4 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra, ranked on a blend of 3 input tokens to 1 output token (USD 0.1062 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Mistral AI sell Mistral Small 3.2 24B Instruct on its own API?
Mistral AI publishes no price for Mistral Small 3.2 24B Instruct on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is DeepInfra at USD 0.075 / USD 0.20 per 1M tokens.
Does Mistral Small 3.2 24B Instruct have cached input pricing?
1 of 4 standard prices includes one. The lowest is USD 0.05 per 1M at Parasail. Providers without one bill cached input at the input price. What cached input means.
What is the Mistral Small 3.2 24B Instruct context window?
Up to 256,000 tokens. 2 standard prices come with less, down to 32,768 tokens (Featherless and DeepInfra). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Mistral Small 3.2 24B Instruct?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 127.80 a month at Parasail, USD 172.13 at the median price and USD 426.46 at Featherless. Try your own numbers.
Is there a batch, flex or priority price for Mistral Small 3.2 24B Instruct?
Yes: flex / spot from DeepInfra at USD 0.06 / USD 0.16; priority from DeepInfra at USD 0.1125 / USD 0.30 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is Mistral Small 3.2 24B Instruct free to use through an API?
No provider in our data lists a free price for Mistral Small 3.2 24B Instruct as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is Mistral Small 3.2 24B Instruct open source, with open weights, and what is its licence?
Mistral AI publishes the weights on Hugging Face as mistralai/Mistral-Small-3.2-24B-Instruct-2506, in a public repository with no access gate. The licence, as the Mistral AI model card metadata states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Mistral AI's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.
How many parameters does Mistral Small 3.2 24B Instruct have?
Mistral AI's model card does not state a total that we found. Hugging Face counts about 24.0 billion (24,011,361,280) parameters in the published weight files of mistralai/Mistral-Small-3.2-24B-Instruct-2506. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).
Does Mistral Small 3.2 24B Instruct support tool calling?
Yes, according to the Mistral AI model card: “Mistral-Small-3.2-24B-Instruct-2506 is excellent at function / tool calling tasks via vLLM.” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.
How do I call Mistral Small 3.2 24B Instruct with the OpenAI SDK?
BroadNet does not serve Mistral Small 3.2 24B Instruct. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: DeepInfra (https://api.deepinfra.com/v1/openai, model mistralai/Mistral-Small-3.2-24B-Instruct-2506). Each provider page quotes the provider's docs with a check date.