Mistralopen weightsMistral Small 3.2 24B pricing
$0.094 per 1M input tokens and $0.25 per 1M output tokens. In real work that is 0.03¢ per chat answer and 0.18¢ to summarize a 20-page PDF.
What Mistral Small 3.2 24B costs per task
Token counts estimated from a measured model of the same lab (Mistral Large 4), rescaled by tokenizer. Reasoning tokens are billed as output.
| Task | Cost | Tokens used | Price rank | Basis |
|---|---|---|---|---|
| Answer a chat question | 0.03¢$0.35 / 1,000 | 40 in · 523 out · 854 reasoning | 35 of 336 | estimated |
| Reply to a customer email | 0.09¢$0.91 / 1,000 | 254 in · 599 out · 2,946 reasoning | 165 of 336 | estimated |
| Write a 1,500-word blog post | 0.19¢$1.95 / 1,000 | 55 in · 2,064 out · 5,705 reasoning | 53 of 336 | estimated |
| Write 10 product descriptions | 0.08¢$0.80 / 1,000 | 285 in · 849 out · 2,230 reasoning | 27 of 336 | estimated |
| Translate 1,000 words | 0.32¢$3.16 / 1,000 | 1,349 in · 1,317 out · 10,816 reasoning | 127 of 336 | estimated |
| Proofread one page (500 words) | 0.11¢$1.10 / 1,000 | 731 in · 860 out · 3,281 reasoning | 100 of 336 | estimated |
| Summarize a 20-page PDF | 0.18¢$1.80 / 1,000 | 13,373 in · 151 out · 2,019 reasoning | 62 of 336 | estimated |
| Extract data from an invoice | 0.07¢$0.70 / 1,000 | 374 in · 871 out · 1,784 reasoning | 77 of 336 | estimated |
| Analyze a 200-row spreadsheet | 0.31¢$3.12 / 1,000 | 4,774 in · 4,526 out · 6,174 reasoning | 35 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.12¢$1.15 / 1,000 | 3,772 in · 210 out · 2,981 reasoning | 69 of 336 | estimated |
| Classify 100 support tickets | 0.20¢$1.97 / 1,000 | 1,274 in · 832 out · 6,565 reasoning | 67 of 336 | estimated |
| Review 500 lines of code | 0.27¢$2.72 / 1,000 | 4,658 in · 1,594 out · 7,522 reasoning | 32 of 336 | estimated |
| Write a SQL query | 0.08¢$0.80 / 1,000 | 121 in · 511 out · 2,647 reasoning | 81 of 336 | estimated |
| Run a 50-step coding agent | 25¢$253 / 1,000 | 2,304,625 in · 15,450 out · 132,350 reasoning | 122 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Mistral Small 3.2 24B through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
 DeepInfrafp8 | $0.075 / $0.20 | - | 128K | 100% |
| V Venicefp8 | $0.094 / $0.25 | - | 256K | 100% |
 Parasailbf16 | $0.09 / $0.30 | $0.05 | 131K | 100% |
Mistralunknown | $0.10 / $0.30 | $0.01 | 32K | 100% |
Price history
First seen in our price history on Jul 1, 2025 at $0.05 input / $0.10 output. Since then the output price moved from $0.10 to $0.25 per 1M tokens (10 changes).
FAQ
How much does Mistral Small 3.2 24B cost?
Mistral Small 3.2 24B costs $0.094 per 1 million input tokens and $0.25 per 1 million output tokens (list price on Oct 18, 2026). In practice one chat answer costs about 0.03¢ and summarizing a 20-page PDF about 0.18¢.
Where is Mistral Small 3.2 24B cheapest?
Among 4 providers we track, the lowest list price today is at DeepInfra: $0.075 input and $0.20 output per 1M tokens.
Is the Mistral Small 3.2 24B cost per task measured or estimated?
Estimated: Mistral Small 3.2 24B was not run directly. Tokens come from Mistral Large 4 and are rescaled by the tokenizer of Mistral. Real usage can differ.