DeepSeek V4 Flash 0731 vs Ministral 3 3B API pricing
Updated
DeepSeek V4 Flash 0731: USD 0.06 input, USD 0.18 output per 1M tokens (DeepInfra and 1 other). Ministral 3 3B: USD 0.10 input, USD 0.10 output per 1M tokens (Mistral AI and 1 other). At 3 input tokens per output token, Ministral 3 3B costs 11% more than DeepSeek V4 Flash 0731 (USD 0.10 vs USD 0.09 per 1M).
How do DeepSeek V4 Flash 0731 and Ministral 3 3B differ on price?
- Cheapest input price: DeepSeek V4 Flash 0731 USD 0.06 against USD 0.10 per 1M tokens, so Ministral 3 3B costs 1.67× as much (67% more).
- Cheapest output price: Ministral 3 3B USD 0.10 against USD 0.18 per 1M tokens, so DeepSeek V4 Flash 0731 costs 1.8× as much (80% more).
- Among the 201 indexed models, DeepSeek V4 Flash 0731 ranks 17th cheapest and Ministral 3 3B 21st on the 3:1 blend.
- The cheaper model changes at 2 input tokens per output token.
- Both list cached-input discounts: DeepSeek V4 Flash 0731 at 17 standard prices of 17, from USD 0.0091 (GMI Cloud, 97% below that provider's input price); Ministral 3 3B at 1 standard price of 2, from USD 0.01 (Mistral AI, 90% below that provider's input price).
- DeepSeek V4 Flash 0731 states up to 1,048,576 tokens of context, 4× the 262,144 of Ministral 3 3B.
- DeepSeek V4 Flash 0731 has 17 providers with a standard price, 15 more than Ministral 3 3B; no provider sells both, so using both means two accounts.
- Shopping around matters more for DeepSeek V4 Flash 0731: its dearest standard price is 7.3× its cheapest, against 1× for Ministral 3 3B.
- Mistral AI's own API is one of 2 providers tied for the lowest standard price we found for Ministral 3 3B, USD 0.10 at 3:1.
- DeepSeek V4 Flash 0731 has a batch price at 1 provider, from USD 0.06 at 3:1 (Doubleword); Ministral 3 3B has a batch price at 1 provider, from USD 0.05 at 3:1 (Mistral AI).
- For the one-developer coding agent preset, the gap is USD 48.60 a year in Ministral 3 3B's favour (DeepSeek V4 Flash 0731 USD 55.35 a month, Ministral 3 3B USD 51.30).
- Per character of input, the gap depends on the language: DeepSeek V4 Flash 0731 costs 9% less than Ministral 3 3B on Hindi text but 61% less than Ministral 3 3B on Chinese, because the two tokenizers split those languages differently.
DeepSeek V4 Flash 0731 and Ministral 3 3B 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 | DeepSeek V4 Flash 0731 | Ministral 3 3B |
|---|---|---|
| Model page | DeepSeek V4 Flash 0731 DeepSeek · 17 providers | Ministral 3 3B Mistral AI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.09 lower USD 0.06 in / USD 0.18 out at DeepInfra and 1 other DeepInfra page checked 2026-11-14 | USD 0.10 USD 0.10 in / USD 0.10 out at Mistral AI and 1 other Mistral AI page checked 2026-11-14 |
| Cheapest input | USD 0.06 lower DeepInfra source | USD 0.10 Mistral AI source |
| Cheapest cached input | USD 0.0091 lower promo GMI Cloud source | USD 0.01 Mistral AI source |
| Cheapest output | USD 0.18 DeepInfra source | USD 0.10 lower Mistral AI source |
| Maker's own API | DeepSeek publishes no paid standard price on its own API that we found. | USD 0.10 / USD 0.10 Mistral AI source |
| Median standard price | USD 0.14 / USD 0.28 input / output, 17 prices | USD 0.10 / USD 0.10 input / output, 2 prices |
| Context window | 1,048,576 tokens, largest stated; from 262,144 at some providers | 262,144 tokens, largest stated |
| Providers with a standard price | 17 | 2 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do DeepSeek V4 Flash 0731 and Ministral 3 3B 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 | DeepSeek V4 Flash 0731 | Ministral 3 3B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 6.21 DeepInfra | USD 5.94 Mistral AI | USD 0.27 Ministral 3 3B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 13.86 DeepInfra | USD 19.02 Mistral AI | USD 5.16 DeepSeek V4 Flash 0731 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 55.35 DeepInfra | USD 51.30 Mistral AI | USD 4.05 Ministral 3 3B lower |
The cheaper model depends on the workload: Ministral 3 3B for Support chatbot, DeepSeek V4 Flash 0731 for RAG over documents, Ministral 3 3B for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on RAG over documents: the dearer model costs 37% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 2 input tokens per output token, Ministral 3 3B is cheaper; above 2, DeepSeek V4 Flash 0731 is cheaper. At the site's 3:1 blend, DeepSeek V4 Flash 0731 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
| Input : output tokens | DeepSeek V4 Flash 0731 | Ministral 3 3B |
|---|---|---|
| 1 : 3 (long answers) | USD 0.15 DeepInfra | USD 0.10 lower Mistral AI |
| 1 : 1 | USD 0.12 DeepInfra | USD 0.10 lower Mistral AI |
| 3 : 1 (the site’s blend) | USD 0.09 lower DeepInfra | USD 0.10 Mistral AI |
| 10 : 1 (retrieval, long prompts) | USD 0.07091 lower DeepInfra | USD 0.10 Mistral AI |
| 30 : 1 (agents, big contexts) | USD 0.06387 lower DeepInfra | USD 0.10 Mistral AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do DeepSeek V4 Flash 0731 and Ministral 3 3B cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the DeepSeek V4.1 Flash tokenizer for DeepSeek V4 Flash 0731 and the Ministral 3 14B tokenizer for Ministral 3 3B:
| Content | DeepSeek V4 Flash 0731 | Ministral 3 3B |
|---|---|---|
| English | USD 0.013 lower DeepInfra | USD 0.022 Amazon Bedrock |
| Arabic MSA | USD 0.023 lower DeepInfra | USD 0.030 Amazon Bedrock |
| Egyptian Arabic | USD 0.023 lower DeepInfra | USD 0.032 Amazon Bedrock |
| Hindi | USD 0.035 lower DeepInfra | USD 0.038 Amazon Bedrock |
| Chinese | USD 0.035 lower DeepInfra | USD 0.090 Amazon Bedrock |
| Spanish | USD 0.015 lower DeepInfra | USD 0.023 Amazon Bedrock |
| Code | USD 0.016 lower DeepInfra | USD 0.027 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
- DeepSeek V4 Flash 0731 API pricing: all 17 providers and other tiers.
- Ministral 3 3B API pricing: all 2 providers and other tiers.
- Cost calculator with DeepSeek V4 Flash 0731 and Ministral 3 3B preloaded
- DeepSeek token counter
- Ministral 3 token counter
- Prompt caching calculator
More comparisons: DeepSeek V4 Flash 0731 vs Gemma 4 26B A4B · DeepSeek V4 Flash 0731 vs DeepSeek V4 Flash · every DeepSeek V4 Flash 0731 comparison · every Ministral 3 3B comparison · all 662 price comparisons
Questions
Is DeepSeek V4 Flash 0731 cheaper than Ministral 3 3B?
Yes. On a blend of 3 input tokens to 1 output token, DeepSeek V4 Flash 0731 costs USD 0.09 per 1M tokens and Ministral 3 3B USD 0.10, at each model's cheapest standard price. For input alone, DeepSeek V4 Flash 0731 is cheaper (USD 0.06 against USD 0.10 per 1M); for output alone, Ministral 3 3B is (USD 0.10 against USD 0.18). This compares price only, not quality.
What do DeepSeek V4 Flash 0731 and Ministral 3 3B cost per 1M tokens?
DeepSeek V4 Flash 0731: from USD 0.06 input and USD 0.18 output at DeepInfra and 1 other; median of 17 standard prices USD 0.14 / USD 0.28. Ministral 3 3B: from USD 0.10 input and USD 0.10 output at Mistral AI and 1 other; Mistral AI's own API charges USD 0.10 / USD 0.10; median of 2 standard prices USD 0.10 / USD 0.10. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both DeepSeek V4 Flash 0731 and Ministral 3 3B?
None of the providers we track sells both at a standard price. DeepSeek V4 Flash 0731 is cheapest at DeepInfra and 1 other and Ministral 3 3B at Mistral AI and 1 other, so running both means two accounts.
Which is cheaper for a coding agent or a chatbot, DeepSeek V4 Flash 0731 or Ministral 3 3B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 55.35 a month on DeepSeek V4 Flash 0731 (DeepInfra) against USD 51.30 on Ministral 3 3B (Mistral AI), a difference of USD 4.05. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 6.21 a month on DeepSeek V4 Flash 0731 (DeepInfra) against USD 5.94 on Ministral 3 3B (Mistral AI), a difference of USD 0.27. 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 DeepSeek V4 Flash 0731 and Ministral 3 3B change?
The cheaper model changes with the mix: below 2 input tokens per output token, Ministral 3 3B is cheaper; above 2, DeepSeek V4 Flash 0731 is cheaper. At the site's 3:1 blend, DeepSeek V4 Flash 0731 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
Do DeepSeek V4 Flash 0731 and Ministral 3 3B have cached input pricing?
DeepSeek V4 Flash 0731 from USD 0.0091 per 1M cached input tokens (GMI Cloud; 17 of 17 standard prices list a discount). Ministral 3 3B from USD 0.01 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, DeepSeek V4 Flash 0731 or Ministral 3 3B?
DeepSeek V4 Flash 0731: up to 1,048,576 tokens, against 262,144 for Ministral 3 3B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.