Ministral 8B

Name: Ministral 8B
Author: MistralAI

Released

2025-06-01

Last refreshed

2026-06-29

Status

Researched 134d ago

ProprietaryCommercial use: unknownClassificationJSON / Tool use

MistralAI releases · 17 in the last 12 months · this family litChangelog →

Specifications

Family: Ministral
Released: 2025-06-01
Context: 32k
Parameters: 8
Openness: Proprietary
Weights: Not released
Code: Unknown

Created by

MistralAI

Enterprise AI solutions for trust and transparency.

Paris, France

Founded 2023

Website

Pricing

Output / 1M

$0.100

Input / 1M

$0.100

Cheapest of 3 routes · AWS Bedrock

Providers(3)

AWS Bedrock Mistral AI Studio Vercel AI Gateway

View 3 provider routes

About

Ministral 8B is MistralAI's Ministral model. It offers a 32K-token context window.

Top use-case fit

JSON / Tool use

Q/$ B

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Batch in / out	Route
AWS Bedrock	$0.100	$0.100	-	Serverless
Mistral AI Studio	$0.150	$0.150	$0.050 / $0.050	Serverless
Vercel AI Gateway	$0.150	$0.150	-	Serverless

Available via routers & gateways(11)

LiteLLM

Gateway

Open-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.

Free OSSMistral AI Studio

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughMistral AI Studio

Portkey

Gateway

Production AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.

SubscriptionMistral AI Studio

AIRouter

Router

Commercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.

Passthrough + feeMistral AI Studio

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Martian

Router

AI-powered LLM router that analyzes each prompt in real-time to select the optimal model, targeting 20–97% cost reduction while maintaining quality; San Francisco startup reportedly nearing $1.3B valuation.

Passthrough + feeMistral AI Studio

Capabilities

Structured Outputs

Benchmark peer barsfor JSON / Tool use

BFCLRank 16 of 17

77.5

73.2

72.9

72.5

11.1

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.