Ministral 3B
Summary
Ministral 3B is an open-weight language model from Mistral AI, released on 16 Oct 2024. It accepts text and images and generates text, with a 131K-token context window and up to 4K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.04 per million input tokens and $0.04 per million output tokens (Azure AI Foundry), across 2 providers we track.
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Mistral AI |
|---|---|
| Release date | 16 Oct 2024 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 4K tokens [models.dev] |
| Knowledge cutoff | Oct 2024 [models.dev] |
| Input | Text and images [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | Yes [models.dev] |
Ministral 3B API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Azure AI Foundry ministral-3b | $0.04 | $0.04 | – | 128K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway mistral/ministral-3b | $0.10 | $0.10 | $0.01 | 131K | models.dev, 18 Nov 2026 |
Frequently asked questions
What is the context window of Ministral 3B?
Ministral 3B has a context window of 131,072 tokens (131K) and can generate up to 4,000 tokens in a single response, according to models.dev.
How much does the Ministral 3B API cost?
Ministral 3B is listed from $0.04 per million input tokens and $0.04 per million output tokens (Azure AI Foundry). Prices last verified 18 Nov 2026.
Is Ministral 3B open source?
Ministral 3B is an open-weight model. Check the license terms before commercial use.
When was Ministral 3B released?
Mistral AI released Ministral 3B on 16 Oct 2024, according to models.dev.
Which providers offer Ministral 3B?
We track Ministral 3B on 2 providers: Azure AI Foundry, Vercel AI Gateway.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Llama 3.2 1B Instruct | Meta | 25 Sept 2024 | 131K | $0.02 | $0.02 | Open |
| Llama 3.1 8B Instruct | Meta | 23 Jul 2024 | 128K | $0.02 | $0.04 | Open |
| Command R7B | Cohere | 13 Dec 2024 | 128K | $0.04 | $0.15 | Open |
| Qwen2.5-Coder-32B-Instruct | Alibaba (Qwen) | 12 Nov 2024 | 131K | $0.06 | $0.20 | Open |
| Gemma 3 12B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.05 | $0.10 | Open |
| Gemma 3 4B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.05 | $0.10 | Open |
Change history
- Context window changed from 128K to 131K
- Input modalities changed from text to text, image
- Knowledge cutoff changed from Mar 2024 to Oct 2024
- Release date changed from 22 Oct 2024 to 16 Oct 2024
- Max output changed from 8K to 4K
- Max output changed from 4K to 8K
- Input modalities changed from text, image to text
- Knowledge cutoff changed from Oct 2024 to Mar 2024
- Release date changed from 16 Oct 2024 to 22 Oct 2024
- Context window changed from 131K to 128K
- Context window changed from 128K to 131K
- Max output changed from 8K to 4K
- Release date changed from 22 Oct 2024 to 16 Oct 2024
- Knowledge cutoff changed from Mar 2024 to Oct 2024
- Input modalities changed from text to text, image
- Context window changed from 131K to 128K
- Input modalities changed from text, image to text
- Knowledge cutoff changed from Oct 2024 to Mar 2024
- Release date changed from 16 Oct 2024 to 22 Oct 2024
- Max output changed from 4K to 8K
- Now listed on Vercel AI Gateway
- Now listed on Azure AI Foundry
- No longer listed on Azure AI Foundry
- No longer listed on Vercel AI Gateway
- Max output changed from 8K to 4K