Mistral Small 3.1 24B vs Mistral-Small-24B-2501 API pricing
Updated
Mistral Small 3.1 24B: USD 0.10 input, USD 0.30 output per 1M tokens (Google Vertex AI). Mistral-Small-24B-2501: USD 0.05 input, USD 0.08 output per 1M tokens (DeepInfra). At 3 input tokens per output token, Mistral Small 3.1 24B costs 2.61× as much as Mistral-Small-24B-2501 (USD 0.15 vs USD 0.0575 per 1M).
How do Mistral Small 3.1 24B and Mistral-Small-24B-2501 differ on price?
- Cheapest input price: Mistral-Small-24B-2501 USD 0.05 against USD 0.10 per 1M tokens, so Mistral Small 3.1 24B costs 2× as much.
- Cheapest output price: Mistral-Small-24B-2501 USD 0.08 against USD 0.30 per 1M tokens, so Mistral Small 3.1 24B costs 3.8× as much.
- Among the 201 indexed models, Mistral Small 3.1 24B ranks 40th cheapest and Mistral-Small-24B-2501 7th on the 3:1 blend.
- No input:output mix changes the answer: Mistral-Small-24B-2501 is cheaper at every mix before cache discounts.
- Only Mistral-Small-24B-2501 lists a cached-input discount: Mistral-Small-24B-2501 at 1 standard price of 2, from USD 0.04 (Featherless, 77% below that provider's input price). Mistral Small 3.1 24B's cached tokens bill at the input price.
- Both state a context window of up to 32,768 tokens.
- Mistral Small 3.1 24B has 4 providers with a standard price, 2 more than Mistral-Small-24B-2501; 1 provider sells both (Featherless).
- On one account, Featherless charges USD 0.2632 for Mistral Small 3.1 24B (1.75× its cheapest price) and USD 0.2037 for Mistral-Small-24B-2501 (3.5× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Mistral-Small-24B-2501: its dearest standard price is 3.5× its cheapest, against 2.7× for Mistral Small 3.1 24B.
- Per character of input, Mistral Small 3.1 24B costs 2× as much as Mistral-Small-24B-2501 in every measured language, because both use the Mistral Small 3.1 tokenizer.
Mistral Small 3.1 24B and Mistral-Small-24B-2501 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 3.1 24B | Mistral-Small-24B-2501 |
|---|---|---|
| Model page | Mistral Small 3.1 24B Instruct Mistral AI · 4 providers | Mistral-Small-24B-Instruct-2501 Mistral AI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.15 USD 0.10 in / USD 0.30 out at Google Vertex AI Google Vertex AI page checked 2026-11-14 | USD 0.0575 lower USD 0.05 in / USD 0.08 out at DeepInfra DeepInfra page checked 2026-11-14 |
| Cheapest input | USD 0.10 Google Vertex AI source | USD 0.05 lower DeepInfra source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | USD 0.04 Featherless source |
| Cheapest output | USD 0.30 Google Vertex AI source | USD 0.08 lower DeepInfra source |
| Maker's own API | Mistral AI publishes no paid standard price on its own API that we found. | Mistral AI publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.1614 / USD 0.36025 input / output, 4 prices | USD 0.1125 / USD 0.185 input / output, 2 prices |
| Context window | 32,768 tokens, largest stated | 32,768 tokens, largest stated |
| Providers with a standard price | 4 | 2 |
- 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 3.1 24B and Mistral-Small-24B-2501 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 3.1 24B | Mistral-Small-24B-2501 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 14.40 Google Vertex AI | USD 5.94 DeepInfra | USD 8.46 Mistral-Small-24B-2501 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 28.50 Google Vertex AI | USD 13.20 DeepInfra | USD 15.30 Mistral-Small-24B-2501 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 207.00 Google Vertex AI | exceeds context | — |
Mistral-Small-24B-2501 is cheaper on 2 workloads. The widest gap is on Support chatbot: the dearer model costs 2.42× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
Mistral-Small-24B-2501 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 3.1 24B's, so the input:output ratio never changes the answer.
| Input : output tokens | Mistral Small 3.1 24B | Mistral-Small-24B-2501 |
|---|---|---|
| 1 : 3 (long answers) | USD 0.25 Google Vertex AI | USD 0.0725 lower DeepInfra |
| 1 : 1 | USD 0.20 Google Vertex AI | USD 0.065 lower DeepInfra |
| 3 : 1 (the site’s blend) | USD 0.15 Google Vertex AI | USD 0.0575 lower DeepInfra |
| 10 : 1 (retrieval, long prompts) | USD 0.1182 Google Vertex AI | USD 0.05273 lower DeepInfra |
| 30 : 1 (agents, big contexts) | USD 0.1065 Google Vertex AI | USD 0.05097 lower 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 3.1 24B and Mistral-Small-24B-2501 cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Mistral Small 3.1 tokenizer for Mistral Small 3.1 24B (the same one for both, so the gap equals the price gap):
| Content | Mistral Small 3.1 24B | Mistral-Small-24B-2501 |
|---|---|---|
| English | USD 0.022 Google Vertex AI | USD 0.011 lower DeepInfra |
| Arabic MSA | USD 0.030 Google Vertex AI | USD 0.015 lower DeepInfra |
| Egyptian Arabic | USD 0.032 Google Vertex AI | USD 0.016 lower DeepInfra |
| Hindi | USD 0.059 Google Vertex AI | USD 0.029 lower DeepInfra |
| Chinese | USD 0.090 Google Vertex AI | USD 0.045 lower DeepInfra |
| Spanish | USD 0.023 Google Vertex AI | USD 0.012 lower DeepInfra |
| Code | USD 0.027 Google Vertex AI | USD 0.014 lower DeepInfra |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- Mistral Small 3.1 24B Instruct API pricing: all 4 providers and other tiers.
- Mistral-Small-24B-Instruct-2501 API pricing: all 2 providers and other tiers.
- Cost calculator with Mistral Small 3.1 24B and Mistral-Small-24B-2501 preloaded
- Mistral Small token counter
- Prompt caching calculator
More comparisons: Mistral Small 3.2 vs Mistral Small 3.1 24B · every Mistral Small 3.1 24B comparison · every Mistral-Small-24B-2501 comparison · all 662 price comparisons
Questions
Is Mistral Small 3.1 24B cheaper than Mistral-Small-24B-2501?
No. On a blend of 3 input tokens to 1 output token, Mistral-Small-24B-2501 costs USD 0.0575 per 1M tokens and Mistral Small 3.1 24B USD 0.15, at each model's cheapest standard price. For input alone, Mistral-Small-24B-2501 is cheaper (USD 0.05 against USD 0.10 per 1M); for output alone, Mistral-Small-24B-2501 is (USD 0.08 against USD 0.30). This compares price only, not quality.
What do Mistral Small 3.1 24B and Mistral-Small-24B-2501 cost per 1M tokens?
Mistral Small 3.1 24B: from USD 0.10 input and USD 0.30 output at Google Vertex AI; median of 4 standard prices USD 0.1614 / USD 0.36025. Mistral-Small-24B-2501: from USD 0.05 input and USD 0.08 output at DeepInfra; median of 2 standard prices USD 0.1125 / USD 0.185. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Mistral Small 3.1 24B and Mistral-Small-24B-2501?
1 provider has a standard price for both: Featherless (USD 0.2632 and USD 0.2037 at 3:1). Buying each model from its own cheapest provider costs USD 0.15 and USD 0.0575.
At what input:output ratio does the cheaper of Mistral Small 3.1 24B and Mistral-Small-24B-2501 change?
Mistral-Small-24B-2501 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 3.1 24B's, so the input:output ratio never changes the answer.
Do Mistral Small 3.1 24B and Mistral-Small-24B-2501 have cached input pricing?
Mistral Small 3.1 24B: no standard price lists a cached-input discount. Mistral-Small-24B-2501 from USD 0.04 per 1M cached input tokens (Featherless; 1 of 2 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 3.1 24B or Mistral-Small-24B-2501?
Both go up to 32,768 tokens on the providers that state it.