ModelBench
Mistral AI logo
Models/Mistral AI

Mistral AI: Ministral 3 8B

Compact open vision-language model for edge deployment, instruction following, and tool use

Source-linked ministral Open weights Apache 2.0 Released 2025-12-02
API record Report
InputT
OutputT
Input price$0.15/M
Output price$0.15/M
Context262.144K
Max output262.144K
Providers2
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Ministral 3 8B
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
DigitalOcean ministral-3-8b-instruct-2512 262.144K 262.144K — — — Tools Docs ↗
Amazon Bedrock mistral.ministral-3-8b-instruct 128K 4.096K $0.15 $0.15 — ToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.15/M

Across 1 priced provider

Median input $0.15/M

Midpoint of listed rates

Highest input $0.15/M

Same as the lowest listed rate

Output range $0.15 – $0.15

Per million output tokens

Amazon Bedrock $0.15/MLowest
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 128K to 262.144K tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
✓ Tool calling Yes
? Structured output Unknown
✓ Attachments Yes
✓ Vision input Yes
✓ Open weights Yes
Creator
Mistral AI
Model family
ministral
Knowledge cutoff
Not documented
License
Apache 2.0
Release date
2025-12-02
Model ID
mistral/ministral-3-8b-instruct-2512

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://model.kyssta.lol/api/v1/models/mistral/ministral-3-8b-instruct-2512
curl
curl "https://model.kyssta.lol/api/v1/models/mistral/ministral-3-8b-instruct-2512"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Ministral 3 8B?

Compact open vision-language model for edge deployment, instruction following, and tool use. It is published by Mistral AI and catalogued here from Models.dev.

How much does Ministral 3 8B cost?

Listed input pricing starts at $0.15 per million tokens from Amazon Bedrock.

What is the context length of Ministral 3 8B?

Ministral 3 8B accepts up to 262.144K tokens of context and returns up to 262.144K output tokens.

Does Ministral 3 8B support tool calling and structured output?

Provider catalogs list support for tool calling, and image input.

Which providers serve Ministral 3 8B?

2 providers list this model: DigitalOcean, Amazon Bedrock.

Are the weights for Ministral 3 8B open?

Yes. The weights are published and downloadable from Hugging Face under the Apache 2.0 license.

When was Ministral 3 8B released?

The catalog records a release date of 2025-12-02, last verified Sep 12, 2026.

More models from Mistral AI

View all →
Mistral: Mistral Small 3

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

32.768K ctx $0.05/M in Mistral: Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

262.144K ctx $0.15/M in Mistral: Ministral 3 3B 2512

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

131.072K ctx $0.1/M in Mistral: Saba

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

32.768K ctx $0.2/M in