Ministral 3 14B vs Ministral 3 8B API pricing
Updated
Ministral 3 14B: USD 0.20 input, USD 0.20 output per 1M tokens (Mistral AI and 2 others). Ministral 3 8B: USD 0.15 input, USD 0.15 output per 1M tokens (Mistral AI and 1 other). At 3 input tokens per output token, Ministral 3 14B costs 33% more than Ministral 3 8B (USD 0.20 vs USD 0.15 per 1M).
How do Ministral 3 14B and Ministral 3 8B differ on price?
- Cheapest input price: Ministral 3 8B USD 0.15 against USD 0.20 per 1M tokens, so Ministral 3 14B costs 1.33× as much (33% more).
- Cheapest output price: Ministral 3 8B USD 0.15 against USD 0.20 per 1M tokens, so Ministral 3 14B costs 1.33× as much (33% more).
- Among the 201 indexed models, Ministral 3 14B ranks 56th cheapest and Ministral 3 8B 40th on the 3:1 blend.
- No input:output mix changes the answer: Ministral 3 8B is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Ministral 3 14B at 2 standard prices of 3, from USD 0.02 (Mistral AI, 90% below that provider's input price); Ministral 3 8B at 1 standard price of 2, from USD 0.015 (Mistral AI, 90% below that provider's input price).
- Both state a context window of up to 262,144 tokens.
- Ministral 3 14B has 3 providers with a standard price, 1 more than Ministral 3 8B; 2 providers sell both (Amazon Bedrock and Mistral AI).
- On one account, Amazon Bedrock charges USD 0.20 for Ministral 3 14B (its cheapest price) and USD 0.15 for Ministral 3 8B (its cheapest price) at 3:1, tied with 1 other provider for the lowest combined price among the providers that sell both.
- Shopping around matters equally: on both, the dearest standard price is 1× the cheapest.
- Mistral AI's own API is one of 3 providers tied for the lowest standard price we found for Ministral 3 14B, USD 0.20 at 3:1.
- Mistral AI's own API is one of 2 providers tied for the lowest standard price we found for Ministral 3 8B, USD 0.15 at 3:1.
- Ministral 3 14B has a batch price at 1 provider, from USD 0.10 at 3:1 (Mistral AI); Ministral 3 8B has a batch price at 1 provider, from USD 0.075 at 3:1 (Mistral AI).
- For the one-developer coding agent preset, the gap is USD 307.80 a year in Ministral 3 8B's favour (Ministral 3 14B USD 102.60 a month, Ministral 3 8B USD 76.95).
- Per character of input, Ministral 3 14B costs 1.33× as much as Ministral 3 8B in every measured language, because both use the Ministral 3 14B tokenizer.
Ministral 3 14B and Ministral 3 8B 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 | Ministral 3 14B | Ministral 3 8B |
|---|---|---|
| Model page | Ministral 3 14B Mistral AI · 3 providers | Ministral 3 8B Mistral AI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.20 USD 0.20 in / USD 0.20 out at Mistral AI and 2 others Mistral AI page checked 2026-11-14 | USD 0.15 lower USD 0.15 in / USD 0.15 out at Mistral AI and 1 other Mistral AI page checked 2026-11-14 |
| Cheapest input | USD 0.20 Mistral AI source | USD 0.15 lower Mistral AI source |
| Cheapest cached input | USD 0.02 Mistral AI source | USD 0.015 lower Mistral AI source |
| Cheapest output | USD 0.20 Mistral AI source | USD 0.15 lower Mistral AI source |
| Maker's own API | USD 0.20 / USD 0.20 Mistral AI source | USD 0.15 / USD 0.15 Mistral AI source |
| Median standard price | USD 0.20 / USD 0.20 input / output, 3 prices | USD 0.15 / USD 0.15 input / output, 2 prices |
| Context window | 262,144 tokens, largest stated | 262,144 tokens, largest stated |
| Providers with a standard price | 3 | 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 Ministral 3 14B and Ministral 3 8B 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 | Ministral 3 14B | Ministral 3 8B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 11.88 Mistral AI | USD 8.91 Mistral AI | USD 2.97 Ministral 3 8B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 38.04 Mistral AI | USD 28.53 Mistral AI | USD 9.51 Ministral 3 8B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 102.60 Mistral AI | USD 76.95 Mistral AI | USD 25.65 Ministral 3 8B lower |
Ministral 3 8B is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 33% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Ministral 3 8B 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 Ministral 3 14B's, so the input:output ratio never changes the answer.
| Input : output tokens | Ministral 3 14B | Ministral 3 8B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.20 Mistral AI | USD 0.15 lower Mistral AI |
| 1 : 1 | USD 0.20 Mistral AI | USD 0.15 lower Mistral AI |
| 3 : 1 (the site’s blend) | USD 0.20 Mistral AI | USD 0.15 lower Mistral AI |
| 10 : 1 (retrieval, long prompts) | USD 0.20 Mistral AI | USD 0.15 lower Mistral AI |
| 30 : 1 (agents, big contexts) | USD 0.20 Mistral AI | USD 0.15 lower Mistral AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Ministral 3 14B and Ministral 3 8B cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Ministral 3 14B tokenizer for Ministral 3 14B (the same one for both, so the gap equals the price gap):
| Content | Ministral 3 14B | Ministral 3 8B |
|---|---|---|
| English | USD 0.044 Amazon Bedrock | USD 0.033 lower Amazon Bedrock |
| Arabic MSA | USD 0.060 Amazon Bedrock | USD 0.045 lower Amazon Bedrock |
| Egyptian Arabic | USD 0.063 Amazon Bedrock | USD 0.047 lower Amazon Bedrock |
| Hindi | USD 0.076 Amazon Bedrock | USD 0.057 lower Amazon Bedrock |
| Chinese | USD 0.180 Amazon Bedrock | USD 0.135 lower Amazon Bedrock |
| Spanish | USD 0.047 Amazon Bedrock | USD 0.035 lower Amazon Bedrock |
| Code | USD 0.054 Amazon Bedrock | USD 0.040 lower Amazon Bedrock |
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
- Ministral 3 14B API pricing: all 3 providers and other tiers.
- Ministral 3 8B API pricing: all 2 providers and other tiers.
- Cost calculator with Ministral 3 14B and Ministral 3 8B preloaded
- Ministral 3 token counter
- Prompt caching calculator
Questions
Is Ministral 3 14B cheaper than Ministral 3 8B?
No. On a blend of 3 input tokens to 1 output token, Ministral 3 8B costs USD 0.15 per 1M tokens and Ministral 3 14B USD 0.20, at each model's cheapest standard price. For input alone, Ministral 3 8B is cheaper (USD 0.15 against USD 0.20 per 1M); for output alone, Ministral 3 8B is (USD 0.15 against USD 0.20). This compares price only, not quality.
What do Ministral 3 14B and Ministral 3 8B cost per 1M tokens?
Ministral 3 14B: from USD 0.20 input and USD 0.20 output at Mistral AI and 2 others; Mistral AI's own API charges USD 0.20 / USD 0.20; median of 3 standard prices USD 0.20 / USD 0.20. Ministral 3 8B: from USD 0.15 input and USD 0.15 output at Mistral AI and 1 other; Mistral AI's own API charges USD 0.15 / USD 0.15; median of 2 standard prices USD 0.15 / USD 0.15. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Ministral 3 14B and Ministral 3 8B?
2 providers have a standard price for both: Amazon Bedrock (USD 0.20 and USD 0.15 at 3:1), Mistral AI (USD 0.20 and USD 0.15 at 3:1). The first 2 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 0.20 and USD 0.15.
Which is cheaper for a coding agent or a chatbot, Ministral 3 14B or Ministral 3 8B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 102.60 a month on Ministral 3 14B (Mistral AI) against USD 76.95 on Ministral 3 8B (Mistral AI), a difference of USD 25.65. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 11.88 a month on Ministral 3 14B (Mistral AI) against USD 8.91 on Ministral 3 8B (Mistral AI), a difference of USD 2.97. 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 Ministral 3 14B and Ministral 3 8B change?
Ministral 3 8B 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 Ministral 3 14B's, so the input:output ratio never changes the answer.
Do Ministral 3 14B and Ministral 3 8B have cached input pricing?
Ministral 3 14B from USD 0.02 per 1M cached input tokens (Mistral AI; 2 of 3 standard prices list a discount). Ministral 3 8B from USD 0.015 per 1M cached input tokens (Mistral AI; 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, Ministral 3 14B or Ministral 3 8B?
Both go up to 262,144 tokens on the providers that state it.