Ministral 3 3B 2512 API pricing
Mistral charges $0.1 per million input tokens and $0.1 per million output tokens for Ministral 3 3B 2512 (ministral-3-3b-2512), and $0.01 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00015.
Ministral 3 3B 2512 price per million tokens
| Token type | Standard |
|---|---|
| Input | $0.1 |
| Cached input | $0.01 |
| Output | $0.1 |
API model id: ministral-3-3b-2512. Ministral 3 3B 2512 supports a 131K-token context window, up to 131K output tokens, image input and tool calling.
What Ministral 3 3B 2512 costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.00005 | $0.05 | $50.00 |
| Typical request (1K in, 500 out) | $0.00015 | $0.15 | $150.00 |
| Long document summary (20K in, 1K out) | $0.0021 | $2.10 | $2,100.00 |
| Coding agent step (50K in, 2K out) | $0.0052 | $5.20 | $5,200.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. Mistral counts tokens with its own tokenizer, so the same text can be a different number of tokens.
How Ministral 3 3B 2512 compares
- For a typical request, Ministral 3 3B 2512 is cheaper than 98% of the other models on apicost.app.
- GPT-5 nano from OpenAI costs $0.05 input and $0.4 output per million tokens, so a typical request is $0.00025: 1.7× the price of Ministral 3 3B 2512.
- Claude Haiku 5.5 from Anthropic costs $0.1 input and $0.5 output per million tokens, so a typical request is $0.00035: 2.3× the price of Ministral 3 3B 2512.
- Gemini 2.5 Flash Lite from Google Gemini costs $0.1 input and $0.4 output per million tokens, so a typical request is $0.0003: 2× the price of Ministral 3 3B 2512.
Ministral 3 3B 2512 price history
Ministral 3 3B 2512 has cost $0.1 per million input tokens and $0.1 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| Ministral 3B 2512 | Mistral | $0.1 | $0.01 | $0.1 | $0.00015 |
| Ministral 3 8B 2512 | Mistral | $0.15 | $0.015 | $0.15 | $0.000225 |
| Ministral 8B 2512 | Mistral | $0.15 | $0.015 | $0.15 | $0.000225 |
| GPT-5 nano | OpenAI | $0.05 | $0.005 | $0.4 | $0.00025 |
| Mistral Small | Mistral | $0.1 | $0.01 | $0.3 | $0.00025 |
| DeepSeek Coder | DeepSeek | $0.14 | $0.014 | $0.28 | $0.00028 |
| Gemini 2.5 Flash Lite | Google Gemini | $0.1 | $0.01 | $0.4 | $0.0003 |
| Ministral 3 14B 2512 | Mistral | $0.2 | $0.02 | $0.2 | $0.0003 |
Other Mistral models
- Codestral 2508 $0.3 / $0.9
- DeepSeek V4 1 Flash 1017 $0.3 / $1.2
- Labs Leanstral 1.5.1 $0 / $0
- Ministral 3 8B 2512 $0.15 / $0.15
- Ministral 3 14B 2512 $0.2 / $0.2
- Ministral 3B 2512 $0.1 / $0.1
- Ministral 8B 2512 $0.15 / $0.15
- Ministral 14B 2512 $0.2 / $0.2
- Mistral Large 3 $0.5 / $1.5
- Mistral Large 4 $0.7 / $2.1
- Mistral Large 2512 $0.5 / $1.5
- Mistral Medium $1.5 / $7.5
- Mistral Small $0.1 / $0.3
- Mistral Tiny $0.25 / $0.25
- Open Mistral Nemo $0.3 / $0.3
Every Mistral model side by side, with batch, caching and long-context prices: Mistral API pricing. Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the Ministral 3 3B 2512 API cost?
Mistral charges $0.1 per million input tokens and $0.1 per million output tokens for Ministral 3 3B 2512 (ministral-3-3b-2512), and $0.01 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00015.
Has the Ministral 3 3B 2512 API price changed?
No. Ministral 3 3B 2512 has cost $0.1 per million input tokens and $0.1 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Is there a cheaper way to use Ministral 3 3B 2512?
Prompt caching lowers the price of input that repeats across requests to $0.01 per million tokens.
What is the context window of Ministral 3 3B 2512?
Ministral 3 3B 2512 accepts up to 131,072 input tokens, roughly 98,000 words of English, and writes up to 131,072 output tokens per response. Filling the whole context window once costs $0.0131 in input tokens.
Is Ministral 3 3B 2512 cheaper than GPT-5 nano?
Yes. GPT-5 nano from OpenAI costs $0.05 input and $0.4 output per million tokens, so a typical request is $0.00025: 1.7× the price of Ministral 3 3B 2512.
Source: Mistral pricing, via the LiteLLM price list.