Model Library
MistralReleased December 2, 2025Ministral 3 8B
Mistral · Released December 2, 2025
Intelligence score
9
At a glance
- Intelligence
- 9
- Speed
- 93.4tokens/sec
- Latency
- 820mstime to first token
- Input price
- $0.15per 1M tokens
- Output price
- $0.15per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 8billions
Summary
Comparison summary
Ministral 3 8B scores 9 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). Ministral 3 8B generates output at 93.4 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Ministral 3 8B costs $0.15 per 1M input tokens (better than average, median: $0.15) and $0.15 per 1M output tokens (very competitive, median: $0.32), based on Mistral's API.
Specifications
Technical specifications
| Model name | Ministral 3 8B |
|---|---|
| Provider | Mistral |
| Release date | December 2, 2025 |
| Intelligence score | 9 |
| Speed | 93.4 tokens/sec |
| Latency (TTFT) | 0.82s |
| Input price | $0.15 / 1M tokens |
| Output price | $0.15 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 8B |
| Reasoning | No |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: ministral-3-8b |
Pricing
Token prices
Price per 1M tokens
Ministral 3 8B, as listed in the catalog record
- Input$0.15
- Output$0.15
| Token type | Price per 1M |
|---|---|
| Input | $0.15 |
| Output | $0.15 |
Model Intelligence legacy profile: ministral-3-8b
FAQ · 20
Frequently asked questions
Ministral 3 8B was released on December 2, 2025.
Ministral 3 8B was created by Mistral.
Ministral 3 8B scores 9 on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
Ministral 3 8B generates output at 93.4 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Ministral 3 8B has a time to first token (TTFT) of 0.82s (based on Mistral's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.54s).
Ministral 3 8B costs $0.15 per 1M input tokens (better than average, median: $0.15) and $0.15 per 1M output tokens (very competitive, median: $0.32), based on Mistral's API.
Ministral 3 8B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens (based on Mistral's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.15 per 1M tokens. Pricing may vary by provider.
When evaluated on the Intelligence Index, Ministral 3 8B generated 19M output tokens, which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 9.5M).
No, Ministral 3 8B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Ministral 3 8B supports text and image input.
Ministral 3 8B supports text output.
Yes, Ministral 3 8B supports image input and can analyze, describe, and answer questions about images.
Yes, Ministral 3 8B is multimodal. It can process text and image input and generate text output.
Ministral 3 8B has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Ministral 3 8B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Ministral 3 8B has 8 billion parameters.
Ministral 3 8B is released under the Apache 2.0 license. This license allows commercial use.
Ministral 3 8B achieves a score of 9 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Ministral 3 8B is available via API through 2 providers.
Ministral 3 8B is available through 2 API providers.