Voxtral Small 24B 2507 pricing
$0.10 per 1M input tokens and $0.30 per 1M output tokens. In real work that is 0.04¢ per chat answer and 0.20¢ to summarize a 20-page PDF.
What Voxtral Small 24B 2507 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 | 0.04¢$0.42 / 1,000 | 40 in · 523 out · 854 reasoning | 49 of 336 | estimated |
| Reply to a customer email | 0.11¢$1.09 / 1,000 | 254 in · 599 out · 2,946 reasoning | 174 of 336 | estimated |
| Write a 1,500-word blog post | 0.23¢$2.34 / 1,000 | 55 in · 2,064 out · 5,705 reasoning | 68 of 336 | estimated |
| Write 10 product descriptions | 0.10¢$0.95 / 1,000 | 285 in · 849 out · 2,230 reasoning | 30 of 336 | estimated |
| Translate 1,000 words | 0.38¢$3.77 / 1,000 | 1,349 in · 1,317 out · 10,816 reasoning | 133 of 336 | estimated |
| Proofread one page (500 words) | 0.13¢$1.32 / 1,000 | 731 in · 860 out · 3,281 reasoning | 113 of 336 | estimated |
| Summarize a 20-page PDF | 0.20¢$1.99 / 1,000 | 13,373 in · 151 out · 2,019 reasoning | 69 of 336 | estimated |
| Extract data from an invoice | 0.08¢$0.83 / 1,000 | 374 in · 871 out · 1,784 reasoning | 88 of 336 | estimated |
| Analyze a 200-row spreadsheet | 0.37¢$3.69 / 1,000 | 4,774 in · 4,526 out · 6,174 reasoning | 45 of 336 | estimated |
| Answer from 5 retrieved documents (RAG) | 0.13¢$1.33 / 1,000 | 3,772 in · 210 out · 2,981 reasoning | 80 of 336 | estimated |
| Classify 100 support tickets | 0.23¢$2.35 / 1,000 | 1,274 in · 832 out · 6,565 reasoning | 83 of 336 | estimated |
| Review 500 lines of code | 0.32¢$3.20 / 1,000 | 4,658 in · 1,594 out · 7,522 reasoning | 40 of 336 | estimated |
| Write a SQL query | 0.10¢$0.96 / 1,000 | 121 in · 511 out · 2,647 reasoning | 102 of 336 | estimated |
| Run a 50-step coding agent | 7.5¢$74.94 / 1,000 | 2,304,625 in · 15,450 out · 132,350 reasoning | 35 of 336 | modeled |
Price at every provider
List prices per 1M tokens (input / output) at each host serving Voxtral Small 24B 2507 through OpenRouter today. Hosts can differ in quantization, context and speed.
| Provider | Input / output | Cached input | Context | Uptime |
|---|---|---|---|---|
Mistralunknown | $0.10 / $0.30 | $0.01 | 32K | 100% |
Mistralunknown | $0.10 / $0.30 | $0.01 | 32K | |
Mistralunknown | $0.11 / $0.33 | $0.011 | 32K |
Price history
First seen in our price history on Oct 31, 2025 at $0.10 input / $0.30 output. The list price has not changed since.
FAQ
How much does Voxtral Small 24B 2507 cost?
Voxtral Small 24B 2507 costs $0.10 per 1 million input tokens and $0.30 per 1 million output tokens, with cached input at $0.01 (list price on Oct 18, 2026). In practice one chat answer costs about 0.04¢ and summarizing a 20-page PDF about 0.20¢.
Where is Voxtral Small 24B 2507 cheapest?
Among 3 providers we track, the lowest list price today is at Mistral: $0.10 input and $0.30 output per 1M tokens.
Is the Voxtral Small 24B 2507 cost per task measured or estimated?
Estimated: Voxtral Small 24B 2507 was not run directly. Tokens come from Mistral Large 4 and are rescaled by the tokenizer of Mistral. Real usage can differ.